< Prev | Home | Model | Random | Next >

Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 6 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')



Text #0

Max Range: 1.2338. Min Range: -1.2338

Max Act: 1.2338. Min Act: -0.0001

Data Index: 1653738 (The Pile)

Max Activating Token Index: 102

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.2338. Min Range: -1.2338

Max Act: 1.0909. Min Act: -0.0001

Data Index: 1600999 (The Pile)

Max Activating Token Index: 892

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.2338. Min Range: -1.2338

Max Act: 0.9399. Min Act: -0.0001

Data Index: 302004 (The Pile)

Max Activating Token Index: 202

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.2338. Min Range: -1.2338

Max Act: 0.9873. Min Act: -0.0001

Data Index: 1330398 (The Pile)

Max Activating Token Index: 871

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.2338. Min Range: -1.2338

Max Act: 0.9162. Min Act: -0.0001

Data Index: 1708063 (The Pile)

Max Activating Token Index: 281

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.2338. Min Range: -1.2338

Max Act: 0.8823. Min Act: -0.0001

Data Index: 1421077 (The Pile)

Max Activating Token Index: 93

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.2338. Min Range: -1.2338

Max Act: 0.8713. Min Act: -0.0001

Data Index: 823951 (The Pile)

Max Activating Token Index: 575

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.2338. Min Range: -1.2338

Max Act: 0.8365. Min Act: -0.0001

Data Index: 1216063 (The Pile)

Max Activating Token Index: 1015

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.2338. Min Range: -1.2338

Max Act: 0.8582. Min Act: -0.0001

Data Index: 833226 (The Pile)

Max Activating Token Index: 242

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.2338. Min Range: -1.2338

Max Act: 0.8554. Min Act: -0.0001

Data Index: 1565635 (The Pile)

Max Activating Token Index: 14

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.2338. Min Range: -1.2338

Max Act: 0.7890. Min Act: -0.0001

Data Index: 295146 (The Pile)

Max Activating Token Index: 627

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.2338. Min Range: -1.2338

Max Act: 0.7770. Min Act: -0.0001

Data Index: 154683 (The Pile)

Max Activating Token Index: 337

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.2338. Min Range: -1.2338

Max Act: 0.8218. Min Act: -0.0001

Data Index: 1329997 (The Pile)

Max Activating Token Index: 318

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.2338. Min Range: -1.2338

Max Act: 0.7718. Min Act: -0.0001

Data Index: 402209 (The Pile)

Max Activating Token Index: 881

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.2338. Min Range: -1.2338

Max Act: 0.8600. Min Act: -0.0001

Data Index: 1794706 (The Pile)

Max Activating Token Index: 427

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.2338. Min Range: -1.2338

Max Act: 0.8217. Min Act: -0.0001

Data Index: 1740009 (The Pile)

Max Activating Token Index: 570

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.2338. Min Range: -1.2338

Max Act: 0.7644. Min Act: -0.0001

Data Index: 1724083 (The Pile)

Max Activating Token Index: 581

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.2338. Min Range: -1.2338

Max Act: 0.8087. Min Act: -0.0001

Data Index: 1869596 (The Pile)

Max Activating Token Index: 266

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.2338. Min Range: -1.2338

Max Act: 0.7263. Min Act: -0.0001

Data Index: 1116468 (The Pile)

Max Activating Token Index: 362

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.2338. Min Range: -1.2338

Max Act: 0.7359. Min Act: -0.0001

Data Index: 1978433 (The Pile)

Max Activating Token Index: 211

Click toggle to see full text

Truncated

Full Text #19