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

Dataset: The Pile

Neuron 889 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: 0.3370. Min Range: -0.3370

Max Act: 0.3370. Min Act: -0.0000

Data Index: 88953 (The Pile)

Max Activating Token Index: 531

Text #1

Max Range: 0.3370. Min Range: -0.3370

Max Act: 0.2558. Min Act: -0.0000

Data Index: 1141282 (The Pile)

Max Activating Token Index: 956

Text #2

Max Range: 0.3370. Min Range: -0.3370

Max Act: 0.3022. Min Act: -0.0000

Data Index: 1811730 (The Pile)

Max Activating Token Index: 510

Text #3

Max Range: 0.3370. Min Range: -0.3370

Max Act: 0.2945. Min Act: -0.0000

Data Index: 1104228 (The Pile)

Max Activating Token Index: 378

Text #4

Max Range: 0.3370. Min Range: -0.3370

Max Act: 0.2858. Min Act: -0.0000

Data Index: 451472 (The Pile)

Max Activating Token Index: 837

Text #5

Max Range: 0.3370. Min Range: -0.3370

Max Act: 0.2638. Min Act: -0.0000

Data Index: 1187474 (The Pile)

Max Activating Token Index: 596

Text #6

Max Range: 0.3370. Min Range: -0.3370

Max Act: 0.2657. Min Act: -0.0000

Data Index: 637251 (The Pile)

Max Activating Token Index: 864

Text #7

Max Range: 0.3370. Min Range: -0.3370

Max Act: 0.2647. Min Act: -0.0000

Data Index: 1033933 (The Pile)

Max Activating Token Index: 394

Text #8

Max Range: 0.3370. Min Range: -0.3370

Max Act: 0.2461. Min Act: -0.0000

Data Index: 1770337 (The Pile)

Max Activating Token Index: 955

Text #9

Max Range: 0.3370. Min Range: -0.3370

Max Act: 0.2443. Min Act: -0.0000

Data Index: 1256172 (The Pile)

Max Activating Token Index: 346

Text #10

Max Range: 0.3370. Min Range: -0.3370

Max Act: 0.2511. Min Act: -0.0000

Data Index: 189751 (The Pile)

Max Activating Token Index: 173

Text #11

Max Range: 0.3370. Min Range: -0.3370

Max Act: 0.2762. Min Act: -0.0000

Data Index: 1979613 (The Pile)

Max Activating Token Index: 249

Text #12

Max Range: 0.3370. Min Range: -0.3370

Max Act: 0.2296. Min Act: -0.0000

Data Index: 656252 (The Pile)

Max Activating Token Index: 684

Text #13

Max Range: 0.3370. Min Range: -0.3370

Max Act: 0.2626. Min Act: -0.0000

Data Index: 1500780 (The Pile)

Max Activating Token Index: 538

Text #14

Max Range: 0.3370. Min Range: -0.3370

Max Act: 0.2535. Min Act: -0.0000

Data Index: 1571979 (The Pile)

Max Activating Token Index: 119

Text #15

Max Range: 0.3370. Min Range: -0.3370

Max Act: 0.2383. Min Act: -0.0000

Data Index: 243554 (The Pile)

Max Activating Token Index: 132

Text #16

Max Range: 0.3370. Min Range: -0.3370

Max Act: 0.2399. Min Act: -0.0000

Data Index: 1275878 (The Pile)

Max Activating Token Index: 630

Text #17

Max Range: 0.3370. Min Range: -0.3370

Max Act: 0.2541. Min Act: -0.0000

Data Index: 1545621 (The Pile)

Max Activating Token Index: 343

Text #18

Max Range: 0.3370. Min Range: -0.3370

Max Act: 0.2550. Min Act: -0.0000

Data Index: 1342067 (The Pile)

Max Activating Token Index: 1005

Text #19

Max Range: 0.3370. Min Range: -0.3370

Max Act: 0.2262. Min Act: -0.0000

Data Index: 1637891 (The Pile)

Max Activating Token Index: 714