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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3999 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3919. Min Range: -1.3919

Max Act: 1.3919. Min Act: -0.0000

Data Index: 673211 (C4 (Web Text))

Max Activating Token Index: 579

Text #1

Max Range: 1.3919. Min Range: -1.3919

Max Act: 1.3305. Min Act: -0.0000

Data Index: 1308961 (C4 (Web Text))

Max Activating Token Index: 726

Text #2

Max Range: 1.3919. Min Range: -1.3919

Max Act: 1.3700. Min Act: -0.0000

Data Index: 452251 (C4 (Web Text))

Max Activating Token Index: 936

Text #3

Max Range: 1.3919. Min Range: -1.3919

Max Act: 1.1352. Min Act: -0.0000

Data Index: 1151227 (C4 (Web Text))

Max Activating Token Index: 1019

Text #4

Max Range: 1.3919. Min Range: -1.3919

Max Act: 1.0639. Min Act: -0.0000

Data Index: 41337 (C4 (Web Text))

Max Activating Token Index: 47

Text #5

Max Range: 1.3919. Min Range: -1.3919

Max Act: 0.9552. Min Act: -0.0000

Data Index: 971327 (C4 (Web Text))

Max Activating Token Index: 237

Text #6

Max Range: 1.3919. Min Range: -1.3919

Max Act: 1.0096. Min Act: -0.0000

Data Index: 632930 (C4 (Web Text))

Max Activating Token Index: 698

Text #7

Max Range: 1.3919. Min Range: -1.3919

Max Act: 0.9491. Min Act: -0.0000

Data Index: 393250 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 1.3919. Min Range: -1.3919

Max Act: 0.9315. Min Act: -0.0000

Data Index: 885017 (C4 (Web Text))

Max Activating Token Index: 920

Text #9

Max Range: 1.3919. Min Range: -1.3919

Max Act: 0.9356. Min Act: -0.0000

Data Index: 524078 (C4 (Web Text))

Max Activating Token Index: 452

Text #10

Max Range: 1.3919. Min Range: -1.3919

Max Act: 0.9294. Min Act: -0.0000

Data Index: 720601 (C4 (Web Text))

Max Activating Token Index: 880

Text #11

Max Range: 1.3919. Min Range: -1.3919

Max Act: 0.9256. Min Act: -0.0000

Data Index: 998195 (C4 (Web Text))

Max Activating Token Index: 879

Text #12

Max Range: 1.3919. Min Range: -1.3919

Max Act: 0.8842. Min Act: -0.0000

Data Index: 335562 (C4 (Web Text))

Max Activating Token Index: 760

Text #13

Max Range: 1.3919. Min Range: -1.3919

Max Act: 0.9051. Min Act: -0.0000

Data Index: 1165015 (C4 (Web Text))

Max Activating Token Index: 505

Text #14

Max Range: 1.3919. Min Range: -1.3919

Max Act: 0.8941. Min Act: -0.0000

Data Index: 447601 (C4 (Web Text))

Max Activating Token Index: 611

Text #15

Max Range: 1.3919. Min Range: -1.3919

Max Act: 0.8777. Min Act: -0.0000

Data Index: 979929 (C4 (Web Text))

Max Activating Token Index: 618

Text #16

Max Range: 1.3919. Min Range: -1.3919

Max Act: 0.8652. Min Act: -0.0000

Data Index: 834768 (C4 (Web Text))

Max Activating Token Index: 864

Text #17

Max Range: 1.3919. Min Range: -1.3919

Max Act: 0.8364. Min Act: -0.0000

Data Index: 91851 (C4 (Web Text))

Max Activating Token Index: 49

Text #18

Max Range: 1.3919. Min Range: -1.3919

Max Act: 0.8623. Min Act: -0.0000

Data Index: 274599 (C4 (Web Text))

Max Activating Token Index: 226

Text #19

Max Range: 1.3919. Min Range: -1.3919

Max Act: 0.8539. Min Act: -0.0000

Data Index: 782248 (C4 (Web Text))

Max Activating Token Index: 650