< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 45 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: 0.9307. Min Range: -0.9307

Max Act: 0.9126. Min Act: -0.0001

Data Index: 847694 (The Pile)

Max Activating Token Index: 572

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.9307. Min Range: -0.9307

Max Act: 0.9307. Min Act: -0.0001

Data Index: 1552896 (The Pile)

Max Activating Token Index: 360

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.9307. Min Range: -0.9307

Max Act: 0.8412. Min Act: -0.0001

Data Index: 230903 (The Pile)

Max Activating Token Index: 493

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.9307. Min Range: -0.9307

Max Act: 0.8209. Min Act: -0.0001

Data Index: 410351 (The Pile)

Max Activating Token Index: 690

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.9307. Min Range: -0.9307

Max Act: 0.7348. Min Act: -0.0001

Data Index: 1611708 (The Pile)

Max Activating Token Index: 888

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.9307. Min Range: -0.9307

Max Act: 0.8062. Min Act: -0.0001

Data Index: 969546 (The Pile)

Max Activating Token Index: 192

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.9307. Min Range: -0.9307

Max Act: 0.7761. Min Act: -0.0001

Data Index: 263302 (The Pile)

Max Activating Token Index: 285

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.9307. Min Range: -0.9307

Max Act: 0.7506. Min Act: -0.0001

Data Index: 41019 (The Pile)

Max Activating Token Index: 541

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.9307. Min Range: -0.9307

Max Act: 0.7852. Min Act: -0.0001

Data Index: 1233990 (The Pile)

Max Activating Token Index: 954

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.9307. Min Range: -0.9307

Max Act: 0.7589. Min Act: -0.0001

Data Index: 1162263 (The Pile)

Max Activating Token Index: 808

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.9307. Min Range: -0.9307

Max Act: 0.7694. Min Act: -0.0001

Data Index: 1596747 (The Pile)

Max Activating Token Index: 891

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.9307. Min Range: -0.9307

Max Act: 0.7489. Min Act: -0.0001

Data Index: 183501 (The Pile)

Max Activating Token Index: 897

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.9307. Min Range: -0.9307

Max Act: 0.7368. Min Act: -0.0001

Data Index: 1709117 (The Pile)

Max Activating Token Index: 297

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.9307. Min Range: -0.9307

Max Act: 0.7275. Min Act: -0.0001

Data Index: 1967045 (The Pile)

Max Activating Token Index: 435

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.9307. Min Range: -0.9307

Max Act: 0.7398. Min Act: -0.0001

Data Index: 1190620 (The Pile)

Max Activating Token Index: 973

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.9307. Min Range: -0.9307

Max Act: 0.7804. Min Act: -0.0001

Data Index: 1812583 (The Pile)

Max Activating Token Index: 176

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.9307. Min Range: -0.9307

Max Act: 0.7435. Min Act: -0.0001

Data Index: 1757729 (The Pile)

Max Activating Token Index: 542

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.9307. Min Range: -0.9307

Max Act: 0.6961. Min Act: -0.0001

Data Index: 300961 (The Pile)

Max Activating Token Index: 924

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.9307. Min Range: -0.9307

Max Act: 0.7902. Min Act: -0.0001

Data Index: 1219898 (The Pile)

Max Activating Token Index: 972

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.9307. Min Range: -0.9307

Max Act: 0.7562. Min Act: -0.0001

Data Index: 912229 (The Pile)

Max Activating Token Index: 475

Click toggle to see full text

Truncated

Full Text #19