Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3269 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.5063. Min Act: -0.0000

Data Index: 1055299 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.5203. Min Act: -0.0000

Data Index: 1005980 (C4 (Web Text))

Max Activating Token Index: 220

Text #2

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4310. Min Act: 0.0000

Data Index: 445088 (C4 (Web Text))

Max Activating Token Index: 123

Text #3

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4450. Min Act: -0.0000

Data Index: 1333440 (C4 (Web Text))

Max Activating Token Index: 422

Text #4

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4601. Min Act: -0.0000

Data Index: 391659 (C4 (Web Text))

Max Activating Token Index: 230

Text #5

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4315. Min Act: -0.0000

Data Index: 1016314 (C4 (Web Text))

Max Activating Token Index: 1013

Text #6

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4201. Min Act: -0.0000

Data Index: 771050 (C4 (Web Text))

Max Activating Token Index: 297

Text #7

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4428. Min Act: -0.0000

Data Index: 103366 (C4 (Web Text))

Max Activating Token Index: 351

Text #8

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4406. Min Act: -0.0000

Data Index: 711317 (C4 (Web Text))

Max Activating Token Index: 371

Text #9

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4538. Min Act: -0.0000

Data Index: 800024 (C4 (Web Text))

Max Activating Token Index: 988

Text #10

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4229. Min Act: -0.0000

Data Index: 624441 (C4 (Web Text))

Max Activating Token Index: 345

Text #11

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4199. Min Act: 0.0000

Data Index: 581285 (C4 (Web Text))

Max Activating Token Index: 511

Text #12

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4190. Min Act: -0.0000

Data Index: 834328 (C4 (Web Text))

Max Activating Token Index: 430

Text #13

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4338. Min Act: -0.0000

Data Index: 1239834 (C4 (Web Text))

Max Activating Token Index: 824

Text #14

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4046. Min Act: -0.0000

Data Index: 840722 (C4 (Web Text))

Max Activating Token Index: 261

Text #15

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4078. Min Act: -0.0000

Data Index: 166191 (C4 (Web Text))

Max Activating Token Index: 896

Text #16

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4092. Min Act: -0.0000

Data Index: 174571 (C4 (Web Text))

Max Activating Token Index: 599

Text #17

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4072. Min Act: -0.0000

Data Index: 63699 (C4 (Web Text))

Max Activating Token Index: 106

Text #18

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4152. Min Act: -0.0000

Data Index: 896179 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4097. Min Act: 0.0001

Data Index: 774676 (C4 (Web Text))

Max Activating Token Index: 39