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

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

Neuron 63 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.3385. Min Act: -0.0001

Data Index: 237963 (C4 (Web Text))

Max Activating Token Index: 736

Text #1

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.3413. Min Act: -0.0001

Data Index: 1143395 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.3316. Min Act: -0.0000

Data Index: 435413 (C4 (Web Text))

Max Activating Token Index: 514

Text #3

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.3303. Min Act: -0.0001

Data Index: 1201166 (C4 (Web Text))

Max Activating Token Index: 354

Text #4

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.3396. Min Act: -0.0000

Data Index: 259477 (C4 (Web Text))

Max Activating Token Index: 492

Text #5

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.3284. Min Act: -0.0001

Data Index: 1136785 (C4 (Web Text))

Max Activating Token Index: 768

Text #6

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.3234. Min Act: -0.0001

Data Index: 854586 (C4 (Web Text))

Max Activating Token Index: 481

Text #7

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.3130. Min Act: -0.0000

Data Index: 524936 (C4 (Web Text))

Max Activating Token Index: 638

Text #8

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.3097. Min Act: -0.0001

Data Index: 836261 (C4 (Web Text))

Max Activating Token Index: 163

Text #9

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.3098. Min Act: -0.0001

Data Index: 1171664 (C4 (Web Text))

Max Activating Token Index: 470

Text #10

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.3217. Min Act: -0.0000

Data Index: 246982 (C4 (Web Text))

Max Activating Token Index: 163

Text #11

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.3073. Min Act: -0.0000

Data Index: 1068291 (C4 (Web Text))

Max Activating Token Index: 795

Text #12

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.3154. Min Act: -0.0000

Data Index: 209537 (C4 (Web Text))

Max Activating Token Index: 640

Text #13

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.3393. Min Act: -0.0001

Data Index: 1285151 (C4 (Web Text))

Max Activating Token Index: 772

Text #14

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.3292. Min Act: -0.0001

Data Index: 1282979 (C4 (Web Text))

Max Activating Token Index: 537

Text #15

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.3059. Min Act: -0.0000

Data Index: 860740 (C4 (Web Text))

Max Activating Token Index: 596

Text #16

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.3273. Min Act: -0.0001

Data Index: 830978 (C4 (Web Text))

Max Activating Token Index: 448

Text #17

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.3059. Min Act: -0.0001

Data Index: 173629 (C4 (Web Text))

Max Activating Token Index: 964

Text #18

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.3065. Min Act: -0.0001

Data Index: 776118 (C4 (Web Text))

Max Activating Token Index: 684

Text #19

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.2938. Min Act: -0.0001

Data Index: 636991 (C4 (Web Text))

Max Activating Token Index: 668