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

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

Neuron 1204 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.5242. Min Range: -3.5242

Max Act: 3.5242. Min Act: -0.0001

Data Index: 1177442 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 3.5242. Min Range: -3.5242

Max Act: 3.4213. Min Act: -0.0001

Data Index: 935206 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 3.5242. Min Range: -3.5242

Max Act: 3.4136. Min Act: -0.0001

Data Index: 21260 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 3.5242. Min Range: -3.5242

Max Act: 3.2900. Min Act: -0.0001

Data Index: 248778 (C4 (Web Text))

Max Activating Token Index: 7

Text #4

Max Range: 3.5242. Min Range: -3.5242

Max Act: 3.2355. Min Act: -0.0001

Data Index: 414579 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 3.5242. Min Range: -3.5242

Max Act: 3.0597. Min Act: -0.0001

Data Index: 1302806 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 3.5242. Min Range: -3.5242

Max Act: 3.1487. Min Act: -0.0001

Data Index: 969477 (C4 (Web Text))

Max Activating Token Index: 32

Text #7

Max Range: 3.5242. Min Range: -3.5242

Max Act: 3.1244. Min Act: -0.0001

Data Index: 313195 (C4 (Web Text))

Max Activating Token Index: 22

Text #8

Max Range: 3.5242. Min Range: -3.5242

Max Act: 3.0641. Min Act: -0.0001

Data Index: 1359322 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 3.5242. Min Range: -3.5242

Max Act: 2.8844. Min Act: -0.0001

Data Index: 745808 (C4 (Web Text))

Max Activating Token Index: 518

Text #10

Max Range: 3.5242. Min Range: -3.5242

Max Act: 3.0217. Min Act: -0.0001

Data Index: 765153 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 3.5242. Min Range: -3.5242

Max Act: 3.0138. Min Act: -0.0001

Data Index: 1047014 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 3.5242. Min Range: -3.5242

Max Act: 2.9604. Min Act: -0.0001

Data Index: 900967 (C4 (Web Text))

Max Activating Token Index: 33

Text #13

Max Range: 3.5242. Min Range: -3.5242

Max Act: 2.9469. Min Act: -0.0001

Data Index: 576357 (C4 (Web Text))

Max Activating Token Index: 55

Text #14

Max Range: 3.5242. Min Range: -3.5242

Max Act: 2.9344. Min Act: -0.0001

Data Index: 169989 (C4 (Web Text))

Max Activating Token Index: 361

Text #15

Max Range: 3.5242. Min Range: -3.5242

Max Act: 2.9252. Min Act: -0.0001

Data Index: 1296369 (C4 (Web Text))

Max Activating Token Index: 506

Text #16

Max Range: 3.5242. Min Range: -3.5242

Max Act: 2.9231. Min Act: -0.0001

Data Index: 269229 (C4 (Web Text))

Max Activating Token Index: 913

Text #17

Max Range: 3.5242. Min Range: -3.5242

Max Act: 2.8918. Min Act: -0.0001

Data Index: 1163387 (C4 (Web Text))

Max Activating Token Index: 892

Text #18

Max Range: 3.5242. Min Range: -3.5242

Max Act: 2.9893. Min Act: -0.0001

Data Index: 409174 (C4 (Web Text))

Max Activating Token Index: 1016

Text #19

Max Range: 3.5242. Min Range: -3.5242

Max Act: 2.8373. Min Act: -0.0001

Data Index: 901030 (C4 (Web Text))

Max Activating Token Index: 164