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

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

Neuron 613 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9440. Min Range: -0.9440

Max Act: 0.9440. Min Act: -0.0001

Data Index: 669723 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 0.9440. Min Range: -0.9440

Max Act: 0.8319. Min Act: -0.0001

Data Index: 1053158 (C4 (Web Text))

Max Activating Token Index: 92

Text #2

Max Range: 0.9440. Min Range: -0.9440

Max Act: 0.7663. Min Act: -0.0001

Data Index: 1159282 (C4 (Web Text))

Max Activating Token Index: 97

Text #3

Max Range: 0.9440. Min Range: -0.9440

Max Act: 0.7236. Min Act: -0.0001

Data Index: 440904 (C4 (Web Text))

Max Activating Token Index: 166

Text #4

Max Range: 0.9440. Min Range: -0.9440

Max Act: 0.7508. Min Act: -0.0001

Data Index: 521465 (C4 (Web Text))

Max Activating Token Index: 668

Text #5

Max Range: 0.9440. Min Range: -0.9440

Max Act: 0.6681. Min Act: -0.0001

Data Index: 401337 (C4 (Web Text))

Max Activating Token Index: 91

Text #6

Max Range: 0.9440. Min Range: -0.9440

Max Act: 0.6613. Min Act: -0.0001

Data Index: 127365 (C4 (Web Text))

Max Activating Token Index: 524

Text #7

Max Range: 0.9440. Min Range: -0.9440

Max Act: 0.6794. Min Act: -0.0001

Data Index: 1071925 (C4 (Web Text))

Max Activating Token Index: 932

Text #8

Max Range: 0.9440. Min Range: -0.9440

Max Act: 0.6551. Min Act: -0.0001

Data Index: 1051707 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 0.9440. Min Range: -0.9440

Max Act: 0.6740. Min Act: -0.0001

Data Index: 848497 (C4 (Web Text))

Max Activating Token Index: 105

Text #10

Max Range: 0.9440. Min Range: -0.9440

Max Act: 0.6981. Min Act: -0.0001

Data Index: 690793 (C4 (Web Text))

Max Activating Token Index: 243

Text #11

Max Range: 0.9440. Min Range: -0.9440

Max Act: 0.6225. Min Act: -0.0001

Data Index: 1098901 (C4 (Web Text))

Max Activating Token Index: 973

Text #12

Max Range: 0.9440. Min Range: -0.9440

Max Act: 0.6186. Min Act: -0.0001

Data Index: 662897 (C4 (Web Text))

Max Activating Token Index: 188

Text #13

Max Range: 0.9440. Min Range: -0.9440

Max Act: 0.5877. Min Act: -0.0001

Data Index: 1170142 (C4 (Web Text))

Max Activating Token Index: 251

Text #14

Max Range: 0.9440. Min Range: -0.9440

Max Act: 0.6103. Min Act: -0.0001

Data Index: 1042266 (C4 (Web Text))

Max Activating Token Index: 818

Text #15

Max Range: 0.9440. Min Range: -0.9440

Max Act: 0.5994. Min Act: -0.0001

Data Index: 1096389 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 0.9440. Min Range: -0.9440

Max Act: 0.5995. Min Act: -0.0001

Data Index: 999933 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 0.9440. Min Range: -0.9440

Max Act: 0.5594. Min Act: -0.0001

Data Index: 759808 (C4 (Web Text))

Max Activating Token Index: 853

Text #18

Max Range: 0.9440. Min Range: -0.9440

Max Act: 0.5737. Min Act: -0.0001

Data Index: 211133 (C4 (Web Text))

Max Activating Token Index: 342

Text #19

Max Range: 0.9440. Min Range: -0.9440

Max Act: 0.5796. Min Act: -0.0001

Data Index: 633338 (C4 (Web Text))

Max Activating Token Index: 194