Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6077 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.6122. Min Range: -1.6122

Max Act: 1.6122. Min Act: -0.0001

Data Index: 1273915 (C4 (Web Text))

Max Activating Token Index: 143

Text #1

Max Range: 1.6122. Min Range: -1.6122

Max Act: 1.5455. Min Act: -0.0001

Data Index: 406339 (C4 (Web Text))

Max Activating Token Index: 210

Text #2

Max Range: 1.6122. Min Range: -1.6122

Max Act: 1.4480. Min Act: -0.0001

Data Index: 1080037 (C4 (Web Text))

Max Activating Token Index: 901

Text #3

Max Range: 1.6122. Min Range: -1.6122

Max Act: 1.5010. Min Act: -0.0001

Data Index: 1063290 (C4 (Web Text))

Max Activating Token Index: 230

Text #4

Max Range: 1.6122. Min Range: -1.6122

Max Act: 1.3497. Min Act: -0.0001

Data Index: 237826 (C4 (Web Text))

Max Activating Token Index: 899

Text #5

Max Range: 1.6122. Min Range: -1.6122

Max Act: 1.4058. Min Act: -0.0001

Data Index: 620779 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 1.6122. Min Range: -1.6122

Max Act: 1.3393. Min Act: -0.0001

Data Index: 1053927 (C4 (Web Text))

Max Activating Token Index: 62

Text #7

Max Range: 1.6122. Min Range: -1.6122

Max Act: 1.3185. Min Act: -0.0001

Data Index: 287708 (C4 (Web Text))

Max Activating Token Index: 364

Text #8

Max Range: 1.6122. Min Range: -1.6122

Max Act: 1.2758. Min Act: -0.0001

Data Index: 900239 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 1.6122. Min Range: -1.6122

Max Act: 1.3231. Min Act: -0.0001

Data Index: 641133 (C4 (Web Text))

Max Activating Token Index: 199

Text #10

Max Range: 1.6122. Min Range: -1.6122

Max Act: 1.2872. Min Act: -0.0001

Data Index: 1282187 (C4 (Web Text))

Max Activating Token Index: 926

Text #11

Max Range: 1.6122. Min Range: -1.6122

Max Act: 1.2607. Min Act: -0.0001

Data Index: 63855 (C4 (Web Text))

Max Activating Token Index: 109

Text #12

Max Range: 1.6122. Min Range: -1.6122

Max Act: 1.3264. Min Act: -0.0001

Data Index: 958819 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 1.6122. Min Range: -1.6122

Max Act: 1.3058. Min Act: -0.0001

Data Index: 64563 (C4 (Web Text))

Max Activating Token Index: 918

Text #14

Max Range: 1.6122. Min Range: -1.6122

Max Act: 1.2475. Min Act: -0.0001

Data Index: 24950 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 1.6122. Min Range: -1.6122

Max Act: 1.2428. Min Act: -0.0001

Data Index: 151290 (C4 (Web Text))

Max Activating Token Index: 139

Text #16

Max Range: 1.6122. Min Range: -1.6122

Max Act: 1.2423. Min Act: -0.0001

Data Index: 811792 (C4 (Web Text))

Max Activating Token Index: 64

Text #17

Max Range: 1.6122. Min Range: -1.6122

Max Act: 1.2779. Min Act: -0.0001

Data Index: 849399 (C4 (Web Text))

Max Activating Token Index: 104

Text #18

Max Range: 1.6122. Min Range: -1.6122

Max Act: 1.2359. Min Act: -0.0001

Data Index: 407114 (C4 (Web Text))

Max Activating Token Index: 190

Text #19

Max Range: 1.6122. Min Range: -1.6122

Max Act: 1.2395. Min Act: -0.0001

Data Index: 1004343 (C4 (Web Text))

Max Activating Token Index: 103