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

Dataset: The Pile

Neuron 2436 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: 1.0332. Min Range: -1.0332

Max Act: 1.0332. Min Act: -0.0000

Data Index: 1945565 (The Pile)

Max Activating Token Index: 568

Text #1

Max Range: 1.0332. Min Range: -1.0332

Max Act: 0.9559. Min Act: -0.0000

Data Index: 1982235 (The Pile)

Max Activating Token Index: 184

Text #2

Max Range: 1.0332. Min Range: -1.0332

Max Act: 0.9570. Min Act: -0.0000

Data Index: 191976 (The Pile)

Max Activating Token Index: 274

Text #3

Max Range: 1.0332. Min Range: -1.0332

Max Act: 0.9225. Min Act: -0.0000

Data Index: 1473349 (The Pile)

Max Activating Token Index: 228

Text #4

Max Range: 1.0332. Min Range: -1.0332

Max Act: 0.8982. Min Act: -0.0000

Data Index: 1806640 (The Pile)

Max Activating Token Index: 1013

Text #5

Max Range: 1.0332. Min Range: -1.0332

Max Act: 0.7685. Min Act: -0.0000

Data Index: 763326 (The Pile)

Max Activating Token Index: 937

Text #6

Max Range: 1.0332. Min Range: -1.0332

Max Act: 0.9132. Min Act: -0.0000

Data Index: 858365 (The Pile)

Max Activating Token Index: 743

Text #7

Max Range: 1.0332. Min Range: -1.0332

Max Act: 0.8117. Min Act: -0.0000

Data Index: 843522 (The Pile)

Max Activating Token Index: 612

Text #8

Max Range: 1.0332. Min Range: -1.0332

Max Act: 0.8341. Min Act: -0.0000

Data Index: 30317 (The Pile)

Max Activating Token Index: 614

Text #9

Max Range: 1.0332. Min Range: -1.0332

Max Act: 0.7532. Min Act: -0.0000

Data Index: 1153817 (The Pile)

Max Activating Token Index: 836

Text #10

Max Range: 1.0332. Min Range: -1.0332

Max Act: 0.7406. Min Act: -0.0000

Data Index: 108814 (The Pile)

Max Activating Token Index: 177

Text #11

Max Range: 1.0332. Min Range: -1.0332

Max Act: 0.7723. Min Act: -0.0000

Data Index: 218050 (The Pile)

Max Activating Token Index: 418

Text #12

Max Range: 1.0332. Min Range: -1.0332

Max Act: 0.7208. Min Act: -0.0000

Data Index: 1402298 (The Pile)

Max Activating Token Index: 830

Text #13

Max Range: 1.0332. Min Range: -1.0332

Max Act: 0.7557. Min Act: -0.0000

Data Index: 1888844 (The Pile)

Max Activating Token Index: 363

Text #14

Max Range: 1.0332. Min Range: -1.0332

Max Act: 0.8385. Min Act: -0.0000

Data Index: 386692 (The Pile)

Max Activating Token Index: 44

Text #15

Max Range: 1.0332. Min Range: -1.0332

Max Act: 0.7807. Min Act: -0.0000

Data Index: 252398 (The Pile)

Max Activating Token Index: 365

Text #16

Max Range: 1.0332. Min Range: -1.0332

Max Act: 0.8214. Min Act: -0.0000

Data Index: 588928 (The Pile)

Max Activating Token Index: 20

Text #17

Max Range: 1.0332. Min Range: -1.0332

Max Act: 0.7722. Min Act: -0.0000

Data Index: 1772483 (The Pile)

Max Activating Token Index: 47

Text #18

Max Range: 1.0332. Min Range: -1.0332

Max Act: 0.7650. Min Act: -0.0000

Data Index: 791229 (The Pile)

Max Activating Token Index: 308

Text #19

Max Range: 1.0332. Min Range: -1.0332

Max Act: 0.7742. Min Act: -0.0000

Data Index: 1458029 (The Pile)

Max Activating Token Index: 571