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

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

Neuron 2475 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1698. Min Act: -0.0000

Data Index: 490164 (C4 (Web Text))

Max Activating Token Index: 183

Text #1

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1467. Min Act: -0.0001

Data Index: 403026 (C4 (Web Text))

Max Activating Token Index: 624

Text #2

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1446. Min Act: -0.0001

Data Index: 209683 (C4 (Web Text))

Max Activating Token Index: 604

Text #3

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1405. Min Act: -0.0001

Data Index: 112817 (C4 (Web Text))

Max Activating Token Index: 71

Text #4

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1302. Min Act: -0.0001

Data Index: 83861 (C4 (Web Text))

Max Activating Token Index: 678

Text #5

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1212. Min Act: -0.0001

Data Index: 1198696 (C4 (Web Text))

Max Activating Token Index: 171

Text #6

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1302. Min Act: -0.0001

Data Index: 1028500 (C4 (Web Text))

Max Activating Token Index: 962

Text #7

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1210. Min Act: -0.0000

Data Index: 516410 (C4 (Web Text))

Max Activating Token Index: 591

Text #8

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1179. Min Act: -0.0000

Data Index: 314994 (C4 (Web Text))

Max Activating Token Index: 865

Text #9

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1217. Min Act: -0.0001

Data Index: 733091 (C4 (Web Text))

Max Activating Token Index: 980

Text #10

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1152. Min Act: -0.0000

Data Index: 1138648 (C4 (Web Text))

Max Activating Token Index: 550

Text #11

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1150. Min Act: -0.0000

Data Index: 632844 (C4 (Web Text))

Max Activating Token Index: 109

Text #12

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1096. Min Act: -0.0001

Data Index: 794613 (C4 (Web Text))

Max Activating Token Index: 650

Text #13

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1051. Min Act: -0.0001

Data Index: 593186 (C4 (Web Text))

Max Activating Token Index: 659

Text #14

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1114. Min Act: -0.0000

Data Index: 22190 (C4 (Web Text))

Max Activating Token Index: 59

Text #15

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1104. Min Act: -0.0000

Data Index: 245245 (C4 (Web Text))

Max Activating Token Index: 292

Text #16

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1135. Min Act: -0.0000

Data Index: 141277 (C4 (Web Text))

Max Activating Token Index: 745

Text #17

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1097. Min Act: -0.0001

Data Index: 331626 (C4 (Web Text))

Max Activating Token Index: 934

Text #18

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1047. Min Act: -0.0001

Data Index: 655339 (C4 (Web Text))

Max Activating Token Index: 405

Text #19

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1087. Min Act: -0.0000

Data Index: 440756 (C4 (Web Text))

Max Activating Token Index: 304