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

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

Neuron 3353 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8160. Min Range: -0.8160

Max Act: 0.8160. Min Act: -0.0001

Data Index: 672029 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 0.8160. Min Range: -0.8160

Max Act: 0.7986. Min Act: -0.0001

Data Index: 1092984 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 0.8160. Min Range: -0.8160

Max Act: 0.7526. Min Act: -0.0001

Data Index: 163341 (C4 (Web Text))

Max Activating Token Index: 55

Text #3

Max Range: 0.8160. Min Range: -0.8160

Max Act: 0.6836. Min Act: -0.0001

Data Index: 1134662 (C4 (Web Text))

Max Activating Token Index: 405

Text #4

Max Range: 0.8160. Min Range: -0.8160

Max Act: 0.6381. Min Act: -0.0001

Data Index: 596507 (C4 (Web Text))

Max Activating Token Index: 137

Text #5

Max Range: 0.8160. Min Range: -0.8160

Max Act: 0.6722. Min Act: -0.0001

Data Index: 254796 (C4 (Web Text))

Max Activating Token Index: 208

Text #6

Max Range: 0.8160. Min Range: -0.8160

Max Act: 0.6921. Min Act: -0.0001

Data Index: 501036 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 0.8160. Min Range: -0.8160

Max Act: 0.6624. Min Act: -0.0001

Data Index: 1342697 (C4 (Web Text))

Max Activating Token Index: 632

Text #8

Max Range: 0.8160. Min Range: -0.8160

Max Act: 0.6835. Min Act: -0.0001

Data Index: 506418 (C4 (Web Text))

Max Activating Token Index: 131

Text #9

Max Range: 0.8160. Min Range: -0.8160

Max Act: 0.5823. Min Act: -0.0001

Data Index: 1254533 (C4 (Web Text))

Max Activating Token Index: 340

Text #10

Max Range: 0.8160. Min Range: -0.8160

Max Act: 0.6591. Min Act: -0.0001

Data Index: 385875 (C4 (Web Text))

Max Activating Token Index: 161

Text #11

Max Range: 0.8160. Min Range: -0.8160

Max Act: 0.6366. Min Act: -0.0001

Data Index: 454268 (C4 (Web Text))

Max Activating Token Index: 408

Text #12

Max Range: 0.8160. Min Range: -0.8160

Max Act: 0.6783. Min Act: -0.0001

Data Index: 190190 (C4 (Web Text))

Max Activating Token Index: 163

Text #13

Max Range: 0.8160. Min Range: -0.8160

Max Act: 0.6370. Min Act: -0.0001

Data Index: 1019958 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 0.8160. Min Range: -0.8160

Max Act: 0.6448. Min Act: -0.0001

Data Index: 652170 (C4 (Web Text))

Max Activating Token Index: 969

Text #15

Max Range: 0.8160. Min Range: -0.8160

Max Act: 0.6222. Min Act: -0.0001

Data Index: 958851 (C4 (Web Text))

Max Activating Token Index: 455

Text #16

Max Range: 0.8160. Min Range: -0.8160

Max Act: 0.6194. Min Act: -0.0001

Data Index: 673910 (C4 (Web Text))

Max Activating Token Index: 174

Text #17

Max Range: 0.8160. Min Range: -0.8160

Max Act: 0.6598. Min Act: -0.0001

Data Index: 1220912 (C4 (Web Text))

Max Activating Token Index: 141

Text #18

Max Range: 0.8160. Min Range: -0.8160

Max Act: 0.6166. Min Act: -0.0001

Data Index: 22398 (C4 (Web Text))

Max Activating Token Index: 153

Text #19

Max Range: 0.8160. Min Range: -0.8160

Max Act: 0.6035. Min Act: -0.0001

Data Index: 347816 (C4 (Web Text))

Max Activating Token Index: 148