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

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

Neuron 5996 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: 0.1152. Min Range: -0.1152

Max Act: 0.1152. Min Act: -0.0001

Data Index: 312772 (C4 (Web Text))

Max Activating Token Index: 921

Text #1

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.1110. Min Act: -0.0001

Data Index: 1195149 (C4 (Web Text))

Max Activating Token Index: 173

Text #2

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.1123. Min Act: -0.0001

Data Index: 1217901 (C4 (Web Text))

Max Activating Token Index: 417

Text #3

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0813. Min Act: -0.0001

Data Index: 1184602 (C4 (Web Text))

Max Activating Token Index: 196

Text #4

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.1014. Min Act: -0.0001

Data Index: 416697 (C4 (Web Text))

Max Activating Token Index: 526

Text #5

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0932. Min Act: -0.0001

Data Index: 899560 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0928. Min Act: -0.0001

Data Index: 78728 (C4 (Web Text))

Max Activating Token Index: 49

Text #7

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0984. Min Act: -0.0001

Data Index: 1301213 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.1026. Min Act: -0.0001

Data Index: 546176 (C4 (Web Text))

Max Activating Token Index: 40

Text #9

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0914. Min Act: -0.0001

Data Index: 1223168 (C4 (Web Text))

Max Activating Token Index: 44

Text #10

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0874. Min Act: -0.0001

Data Index: 711610 (C4 (Web Text))

Max Activating Token Index: 486

Text #11

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.1125. Min Act: -0.0001

Data Index: 51838 (C4 (Web Text))

Max Activating Token Index: 371

Text #12

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0943. Min Act: -0.0001

Data Index: 141463 (C4 (Web Text))

Max Activating Token Index: 62

Text #13

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0925. Min Act: -0.0001

Data Index: 1312649 (C4 (Web Text))

Max Activating Token Index: 599

Text #14

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0893. Min Act: -0.0001

Data Index: 220382 (C4 (Web Text))

Max Activating Token Index: 112

Text #15

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0714. Min Act: -0.0001

Data Index: 312725 (C4 (Web Text))

Max Activating Token Index: 542

Text #16

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0830. Min Act: -0.0001

Data Index: 576368 (C4 (Web Text))

Max Activating Token Index: 857

Text #17

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0883. Min Act: -0.0001

Data Index: 290545 (C4 (Web Text))

Max Activating Token Index: 82

Text #18

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0789. Min Act: -0.0001

Data Index: 954020 (C4 (Web Text))

Max Activating Token Index: 131

Text #19

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0997. Min Act: -0.0001

Data Index: 401709 (C4 (Web Text))

Max Activating Token Index: 885