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

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

Neuron 3289 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8191. Min Range: -0.8191

Max Act: 0.8064. Min Act: -0.0001

Data Index: 118551 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 0.8191. Min Range: -0.8191

Max Act: 0.8191. Min Act: -0.0002

Data Index: 388167 (C4 (Web Text))

Max Activating Token Index: 553

Text #2

Max Range: 0.8191. Min Range: -0.8191

Max Act: 0.7843. Min Act: -0.0002

Data Index: 105924 (C4 (Web Text))

Max Activating Token Index: 274

Text #3

Max Range: 0.8191. Min Range: -0.8191

Max Act: 0.7015. Min Act: -0.0001

Data Index: 1208225 (C4 (Web Text))

Max Activating Token Index: 891

Text #4

Max Range: 0.8191. Min Range: -0.8191

Max Act: 0.6855. Min Act: -0.0001

Data Index: 1274951 (C4 (Web Text))

Max Activating Token Index: 149

Text #5

Max Range: 0.8191. Min Range: -0.8191

Max Act: 0.6963. Min Act: -0.0001

Data Index: 896892 (C4 (Web Text))

Max Activating Token Index: 158

Text #6

Max Range: 0.8191. Min Range: -0.8191

Max Act: 0.7016. Min Act: -0.0001

Data Index: 1030589 (C4 (Web Text))

Max Activating Token Index: 30

Text #7

Max Range: 0.8191. Min Range: -0.8191

Max Act: 0.6778. Min Act: -0.0002

Data Index: 69199 (C4 (Web Text))

Max Activating Token Index: 574

Text #8

Max Range: 0.8191. Min Range: -0.8191

Max Act: 0.6690. Min Act: -0.0002

Data Index: 1324880 (C4 (Web Text))

Max Activating Token Index: 601

Text #9

Max Range: 0.8191. Min Range: -0.8191

Max Act: 0.6836. Min Act: -0.0002

Data Index: 463206 (C4 (Web Text))

Max Activating Token Index: 22

Text #10

Max Range: 0.8191. Min Range: -0.8191

Max Act: 0.6811. Min Act: -0.0001

Data Index: 385003 (C4 (Web Text))

Max Activating Token Index: 151

Text #11

Max Range: 0.8191. Min Range: -0.8191

Max Act: 0.6599. Min Act: -0.0001

Data Index: 1473880 (Python Code)

Max Activating Token Index: 104

Text #12

Max Range: 0.8191. Min Range: -0.8191

Max Act: 0.6301. Min Act: -0.0001

Data Index: 1244184 (C4 (Web Text))

Max Activating Token Index: 518

Text #13

Max Range: 0.8191. Min Range: -0.8191

Max Act: 0.6717. Min Act: -0.0001

Data Index: 1203228 (C4 (Web Text))

Max Activating Token Index: 691

Text #14

Max Range: 0.8191. Min Range: -0.8191

Max Act: 0.6463. Min Act: -0.0001

Data Index: 565424 (C4 (Web Text))

Max Activating Token Index: 121

Text #15

Max Range: 0.8191. Min Range: -0.8191

Max Act: 0.6576. Min Act: -0.0001

Data Index: 228686 (C4 (Web Text))

Max Activating Token Index: 15

Text #16

Max Range: 0.8191. Min Range: -0.8191

Max Act: 0.6383. Min Act: -0.0002

Data Index: 1206103 (C4 (Web Text))

Max Activating Token Index: 231

Text #17

Max Range: 0.8191. Min Range: -0.8191

Max Act: 0.6363. Min Act: -0.0002

Data Index: 717978 (C4 (Web Text))

Max Activating Token Index: 845

Text #18

Max Range: 0.8191. Min Range: -0.8191

Max Act: 0.5853. Min Act: -0.0001

Data Index: 1325416 (C4 (Web Text))

Max Activating Token Index: 197

Text #19

Max Range: 0.8191. Min Range: -0.8191

Max Act: 0.6799. Min Act: -0.0002

Data Index: 573989 (C4 (Web Text))

Max Activating Token Index: 208