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

Dataset: The Pile

Neuron 3345 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0265. Min Range: -1.0265

Max Act: 1.0265. Min Act: -0.0000

Data Index: 426866 (The Pile)

Max Activating Token Index: 377

Text #1

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.9091. Min Act: -0.0000

Data Index: 1182473 (The Pile)

Max Activating Token Index: 215

Text #2

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.8159. Min Act: -0.0000

Data Index: 1921941 (The Pile)

Max Activating Token Index: 621

Text #3

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.8307. Min Act: -0.0000

Data Index: 1289884 (The Pile)

Max Activating Token Index: 361

Text #4

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.8182. Min Act: -0.0000

Data Index: 931296 (The Pile)

Max Activating Token Index: 667

Text #5

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.7586. Min Act: -0.0000

Data Index: 1373386 (The Pile)

Max Activating Token Index: 928

Text #6

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.8458. Min Act: -0.0000

Data Index: 828688 (The Pile)

Max Activating Token Index: 418

Text #7

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.7950. Min Act: -0.0000

Data Index: 39897 (The Pile)

Max Activating Token Index: 884

Text #8

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.8134. Min Act: -0.0000

Data Index: 1206810 (The Pile)

Max Activating Token Index: 1014

Text #9

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.8283. Min Act: -0.0000

Data Index: 1141907 (The Pile)

Max Activating Token Index: 828

Text #10

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.7062. Min Act: -0.0000

Data Index: 549734 (The Pile)

Max Activating Token Index: 90

Text #11

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.8345. Min Act: -0.0000

Data Index: 1402908 (The Pile)

Max Activating Token Index: 40

Text #12

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.8278. Min Act: -0.0000

Data Index: 559356 (The Pile)

Max Activating Token Index: 834

Text #13

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.6815. Min Act: -0.0000

Data Index: 1462991 (The Pile)

Max Activating Token Index: 508

Text #14

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.7630. Min Act: -0.0000

Data Index: 520395 (The Pile)

Max Activating Token Index: 971

Text #15

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.8089. Min Act: -0.0000

Data Index: 40425 (The Pile)

Max Activating Token Index: 187

Text #16

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.7626. Min Act: -0.0000

Data Index: 1160904 (The Pile)

Max Activating Token Index: 576

Text #17

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.7688. Min Act: -0.0000

Data Index: 628637 (The Pile)

Max Activating Token Index: 33

Text #18

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.8132. Min Act: -0.0000

Data Index: 1715124 (The Pile)

Max Activating Token Index: 163

Text #19

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.8113. Min Act: -0.0000

Data Index: 1360259 (The Pile)

Max Activating Token Index: 675