Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3195 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.9518. Min Range: -3.9518

Max Act: 3.9518. Min Act: -0.0000

Data Index: 1320101 (The Pile)

Max Activating Token Index: 939

Text #1

Max Range: 3.9518. Min Range: -3.9518

Max Act: 3.6196. Min Act: -0.0000

Data Index: 1094886 (The Pile)

Max Activating Token Index: 699

Text #2

Max Range: 3.9518. Min Range: -3.9518

Max Act: 3.5526. Min Act: -0.0000

Data Index: 1553665 (The Pile)

Max Activating Token Index: 588

Text #3

Max Range: 3.9518. Min Range: -3.9518

Max Act: 3.6710. Min Act: -0.0000

Data Index: 1103627 (The Pile)

Max Activating Token Index: 454

Text #4

Max Range: 3.9518. Min Range: -3.9518

Max Act: 3.3389. Min Act: -0.0000

Data Index: 729771 (The Pile)

Max Activating Token Index: 475

Text #5

Max Range: 3.9518. Min Range: -3.9518

Max Act: 3.3205. Min Act: -0.0000

Data Index: 863371 (The Pile)

Max Activating Token Index: 411

Text #6

Max Range: 3.9518. Min Range: -3.9518

Max Act: 3.1314. Min Act: -0.0000

Data Index: 1990844 (The Pile)

Max Activating Token Index: 879

Text #7

Max Range: 3.9518. Min Range: -3.9518

Max Act: 3.4143. Min Act: -0.0000

Data Index: 386866 (The Pile)

Max Activating Token Index: 490

Text #8

Max Range: 3.9518. Min Range: -3.9518

Max Act: 3.3648. Min Act: -0.0000

Data Index: 1437071 (The Pile)

Max Activating Token Index: 890

Text #9

Max Range: 3.9518. Min Range: -3.9518

Max Act: 3.3188. Min Act: -0.0000

Data Index: 538014 (The Pile)

Max Activating Token Index: 297

Text #10

Max Range: 3.9518. Min Range: -3.9518

Max Act: 3.4468. Min Act: -0.0000

Data Index: 1046481 (The Pile)

Max Activating Token Index: 288

Text #11

Max Range: 3.9518. Min Range: -3.9518

Max Act: 3.0819. Min Act: -0.0000

Data Index: 531489 (The Pile)

Max Activating Token Index: 894

Text #12

Max Range: 3.9518. Min Range: -3.9518

Max Act: 3.3375. Min Act: -0.0000

Data Index: 1247231 (The Pile)

Max Activating Token Index: 295

Text #13

Max Range: 3.9518. Min Range: -3.9518

Max Act: 2.7310. Min Act: -0.0000

Data Index: 381754 (The Pile)

Max Activating Token Index: 1012

Text #14

Max Range: 3.9518. Min Range: -3.9518

Max Act: 3.2096. Min Act: -0.0000

Data Index: 878456 (The Pile)

Max Activating Token Index: 375

Text #15

Max Range: 3.9518. Min Range: -3.9518

Max Act: 3.0787. Min Act: -0.0000

Data Index: 1107829 (The Pile)

Max Activating Token Index: 186

Text #16

Max Range: 3.9518. Min Range: -3.9518

Max Act: 3.2289. Min Act: -0.0000

Data Index: 527126 (The Pile)

Max Activating Token Index: 524

Text #17

Max Range: 3.9518. Min Range: -3.9518

Max Act: 2.9348. Min Act: -0.0000

Data Index: 1839132 (The Pile)

Max Activating Token Index: 395

Text #18

Max Range: 3.9518. Min Range: -3.9518

Max Act: 3.0413. Min Act: -0.0000

Data Index: 1252300 (The Pile)

Max Activating Token Index: 336

Text #19

Max Range: 3.9518. Min Range: -3.9518

Max Act: 3.0155. Min Act: -0.0000

Data Index: 1973086 (The Pile)

Max Activating Token Index: 234