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

Dataset: The Pile

Neuron 4238 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8275. Min Range: -1.8275

Max Act: 1.8275. Min Act: -0.0000

Data Index: 1985260 (The Pile)

Max Activating Token Index: 658

Text #1

Max Range: 1.8275. Min Range: -1.8275

Max Act: 1.6340. Min Act: -0.0000

Data Index: 1079031 (The Pile)

Max Activating Token Index: 412

Text #2

Max Range: 1.8275. Min Range: -1.8275

Max Act: 1.4578. Min Act: -0.0000

Data Index: 492209 (The Pile)

Max Activating Token Index: 793

Text #3

Max Range: 1.8275. Min Range: -1.8275

Max Act: 1.3233. Min Act: -0.0000

Data Index: 148547 (The Pile)

Max Activating Token Index: 186

Text #4

Max Range: 1.8275. Min Range: -1.8275

Max Act: 1.3762. Min Act: -0.0000

Data Index: 1241290 (The Pile)

Max Activating Token Index: 505

Text #5

Max Range: 1.8275. Min Range: -1.8275

Max Act: 1.3015. Min Act: -0.0000

Data Index: 1329726 (The Pile)

Max Activating Token Index: 799

Text #6

Max Range: 1.8275. Min Range: -1.8275

Max Act: 1.1414. Min Act: -0.0000

Data Index: 1494962 (The Pile)

Max Activating Token Index: 218

Text #7

Max Range: 1.8275. Min Range: -1.8275

Max Act: 1.1960. Min Act: -0.0000

Data Index: 356159 (The Pile)

Max Activating Token Index: 461

Text #8

Max Range: 1.8275. Min Range: -1.8275

Max Act: 1.1933. Min Act: -0.0000

Data Index: 1930536 (The Pile)

Max Activating Token Index: 165

Text #9

Max Range: 1.8275. Min Range: -1.8275

Max Act: 1.1364. Min Act: -0.0000

Data Index: 502239 (The Pile)

Max Activating Token Index: 588

Text #10

Max Range: 1.8275. Min Range: -1.8275

Max Act: 1.0995. Min Act: -0.0000

Data Index: 214752 (The Pile)

Max Activating Token Index: 577

Text #11

Max Range: 1.8275. Min Range: -1.8275

Max Act: 1.1042. Min Act: -0.0000

Data Index: 86693 (The Pile)

Max Activating Token Index: 31

Text #12

Max Range: 1.8275. Min Range: -1.8275

Max Act: 1.0167. Min Act: -0.0000

Data Index: 1364932 (The Pile)

Max Activating Token Index: 430

Text #13

Max Range: 1.8275. Min Range: -1.8275

Max Act: 1.0132. Min Act: -0.0000

Data Index: 1869816 (The Pile)

Max Activating Token Index: 809

Text #14

Max Range: 1.8275. Min Range: -1.8275

Max Act: 1.1395. Min Act: -0.0000

Data Index: 1108676 (The Pile)

Max Activating Token Index: 583

Text #15

Max Range: 1.8275. Min Range: -1.8275

Max Act: 1.0771. Min Act: -0.0000

Data Index: 211553 (The Pile)

Max Activating Token Index: 679

Text #16

Max Range: 1.8275. Min Range: -1.8275

Max Act: 0.9421. Min Act: -0.0000

Data Index: 1802831 (The Pile)

Max Activating Token Index: 937

Text #17

Max Range: 1.8275. Min Range: -1.8275

Max Act: 1.0338. Min Act: -0.0000

Data Index: 936098 (The Pile)

Max Activating Token Index: 470

Text #18

Max Range: 1.8275. Min Range: -1.8275

Max Act: 0.9722. Min Act: -0.0000

Data Index: 1158949 (The Pile)

Max Activating Token Index: 585

Text #19

Max Range: 1.8275. Min Range: -1.8275

Max Act: 0.9728. Min Act: -0.0000

Data Index: 1214665 (The Pile)

Max Activating Token Index: 457