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

Dataset: The Pile

Neuron 4445 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5760. Min Range: -0.5760

Max Act: 0.5760. Min Act: -0.0000

Data Index: 823760 (The Pile)

Max Activating Token Index: 445

Text #1

Max Range: 0.5760. Min Range: -0.5760

Max Act: 0.5477. Min Act: -0.0000

Data Index: 1022546 (The Pile)

Max Activating Token Index: 679

Text #2

Max Range: 0.5760. Min Range: -0.5760

Max Act: 0.3341. Min Act: -0.0000

Data Index: 616470 (The Pile)

Max Activating Token Index: 381

Text #3

Max Range: 0.5760. Min Range: -0.5760

Max Act: 0.3059. Min Act: -0.0000

Data Index: 1864637 (The Pile)

Max Activating Token Index: 162

Text #4

Max Range: 0.5760. Min Range: -0.5760

Max Act: 0.3508. Min Act: -0.0000

Data Index: 1649982 (The Pile)

Max Activating Token Index: 820

Text #5

Max Range: 0.5760. Min Range: -0.5760

Max Act: 0.3222. Min Act: -0.0000

Data Index: 1202894 (The Pile)

Max Activating Token Index: 925

Text #6

Max Range: 0.5760. Min Range: -0.5760

Max Act: 0.2955. Min Act: -0.0000

Data Index: 1500468 (The Pile)

Max Activating Token Index: 598

Text #7

Max Range: 0.5760. Min Range: -0.5760

Max Act: 0.3583. Min Act: -0.0000

Data Index: 1671998 (The Pile)

Max Activating Token Index: 916

Text #8

Max Range: 0.5760. Min Range: -0.5760

Max Act: 0.3336. Min Act: -0.0000

Data Index: 1698775 (The Pile)

Max Activating Token Index: 545

Text #9

Max Range: 0.5760. Min Range: -0.5760

Max Act: 0.3009. Min Act: -0.0000

Data Index: 220716 (The Pile)

Max Activating Token Index: 337

Text #10

Max Range: 0.5760. Min Range: -0.5760

Max Act: 0.3113. Min Act: -0.0000

Data Index: 742310 (The Pile)

Max Activating Token Index: 133

Text #11

Max Range: 0.5760. Min Range: -0.5760

Max Act: 0.3305. Min Act: -0.0000

Data Index: 977763 (The Pile)

Max Activating Token Index: 170

Text #12

Max Range: 0.5760. Min Range: -0.5760

Max Act: 0.3156. Min Act: -0.0000

Data Index: 526591 (The Pile)

Max Activating Token Index: 506

Text #13

Max Range: 0.5760. Min Range: -0.5760

Max Act: 0.3268. Min Act: -0.0000

Data Index: 571650 (The Pile)

Max Activating Token Index: 200

Text #14

Max Range: 0.5760. Min Range: -0.5760

Max Act: 0.3235. Min Act: -0.0000

Data Index: 1719268 (The Pile)

Max Activating Token Index: 308

Text #15

Max Range: 0.5760. Min Range: -0.5760

Max Act: 0.3331. Min Act: -0.0000

Data Index: 1207713 (The Pile)

Max Activating Token Index: 855

Text #16

Max Range: 0.5760. Min Range: -0.5760

Max Act: 0.3102. Min Act: -0.0000

Data Index: 59424 (The Pile)

Max Activating Token Index: 666

Text #17

Max Range: 0.5760. Min Range: -0.5760

Max Act: 0.3195. Min Act: -0.0000

Data Index: 40310 (The Pile)

Max Activating Token Index: 568

Text #18

Max Range: 0.5760. Min Range: -0.5760

Max Act: 0.2872. Min Act: -0.0000

Data Index: 103374 (The Pile)

Max Activating Token Index: 211

Text #19

Max Range: 0.5760. Min Range: -0.5760

Max Act: 0.3210. Min Act: -0.0000

Data Index: 618869 (The Pile)

Max Activating Token Index: 835