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

Dataset: The Pile

Neuron 1303 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: 0.5277. Min Range: -0.5277

Max Act: 0.5143. Min Act: -0.0000

Data Index: 409420 (The Pile)

Max Activating Token Index: 765

Text #1

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.4640. Min Act: -0.0000

Data Index: 980160 (The Pile)

Max Activating Token Index: 611

Text #2

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.4920. Min Act: -0.0000

Data Index: 1311715 (The Pile)

Max Activating Token Index: 902

Text #3

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.4535. Min Act: -0.0000

Data Index: 25528 (The Pile)

Max Activating Token Index: 591

Text #4

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.4967. Min Act: -0.0000

Data Index: 193228 (The Pile)

Max Activating Token Index: 336

Text #5

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.4536. Min Act: -0.0000

Data Index: 1943386 (The Pile)

Max Activating Token Index: 727

Text #6

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.4638. Min Act: -0.0000

Data Index: 1036134 (The Pile)

Max Activating Token Index: 920

Text #7

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.5105. Min Act: -0.0000

Data Index: 471217 (The Pile)

Max Activating Token Index: 81

Text #8

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.5277. Min Act: -0.0000

Data Index: 94211 (The Pile)

Max Activating Token Index: 491

Text #9

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.4545. Min Act: -0.0000

Data Index: 1539526 (The Pile)

Max Activating Token Index: 1001

Text #10

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.4638. Min Act: -0.0000

Data Index: 791642 (The Pile)

Max Activating Token Index: 217

Text #11

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.4636. Min Act: -0.0000

Data Index: 1760431 (The Pile)

Max Activating Token Index: 428

Text #12

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.4207. Min Act: -0.0000

Data Index: 1958067 (The Pile)

Max Activating Token Index: 442

Text #13

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.4413. Min Act: -0.0000

Data Index: 1328428 (The Pile)

Max Activating Token Index: 586

Text #14

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.4804. Min Act: -0.0000

Data Index: 68054 (The Pile)

Max Activating Token Index: 498

Text #15

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.4712. Min Act: -0.0000

Data Index: 1006295 (The Pile)

Max Activating Token Index: 78

Text #16

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.4339. Min Act: -0.0000

Data Index: 346110 (The Pile)

Max Activating Token Index: 361

Text #17

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.4346. Min Act: -0.0000

Data Index: 1122739 (The Pile)

Max Activating Token Index: 409

Text #18

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.4468. Min Act: -0.0000

Data Index: 1395798 (The Pile)

Max Activating Token Index: 89

Text #19

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.4615. Min Act: -0.0000

Data Index: 597144 (The Pile)

Max Activating Token Index: 387