< Prev | Home | Model | Random | Next >

Model: SoLU Model: 2 Layers, 2944 Neurons per Layer

Dataset: The Pile

Neuron 52 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l-pile')



Text #0

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.5152. Min Act: -0.0002

Data Index: 1929958 (The Pile)

Max Activating Token Index: 419

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.4775. Min Act: -0.0002

Data Index: 701843 (The Pile)

Max Activating Token Index: 293

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.4737. Min Act: -0.0002

Data Index: 1185447 (The Pile)

Max Activating Token Index: 389

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.4671. Min Act: -0.0002

Data Index: 1905287 (The Pile)

Max Activating Token Index: 145

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.4655. Min Act: -0.0002

Data Index: 1983003 (The Pile)

Max Activating Token Index: 685

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.4600. Min Act: -0.0002

Data Index: 374517 (The Pile)

Max Activating Token Index: 338

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.4239. Min Act: -0.0002

Data Index: 1031820 (The Pile)

Max Activating Token Index: 248

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.4633. Min Act: -0.0002

Data Index: 1186519 (The Pile)

Max Activating Token Index: 1004

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.4315. Min Act: -0.0002

Data Index: 534333 (The Pile)

Max Activating Token Index: 707

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.4379. Min Act: -0.0002

Data Index: 671761 (The Pile)

Max Activating Token Index: 190

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.4368. Min Act: -0.0002

Data Index: 315963 (The Pile)

Max Activating Token Index: 168

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.4512. Min Act: -0.0002

Data Index: 504541 (The Pile)

Max Activating Token Index: 400

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.4357. Min Act: -0.0002

Data Index: 748008 (The Pile)

Max Activating Token Index: 236

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.4147. Min Act: -0.0002

Data Index: 352458 (The Pile)

Max Activating Token Index: 152

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.4055. Min Act: -0.0002

Data Index: 1439122 (The Pile)

Max Activating Token Index: 863

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.4079. Min Act: -0.0002

Data Index: 1994573 (The Pile)

Max Activating Token Index: 275

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.4068. Min Act: -0.0002

Data Index: 1281945 (The Pile)

Max Activating Token Index: 471

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.4024. Min Act: -0.0002

Data Index: 30830 (The Pile)

Max Activating Token Index: 311

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.4033. Min Act: -0.0002

Data Index: 20214 (The Pile)

Max Activating Token Index: 164

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.3881. Min Act: -0.0002

Data Index: 1912623 (The Pile)

Max Activating Token Index: 417

Click toggle to see full text

Truncated

Full Text #19