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

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

Neuron 134 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5176. Min Range: -1.5176

Max Act: 1.5176. Min Act: -0.0001

Data Index: 333071 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 1.5176. Min Range: -1.5176

Max Act: 1.2507. Min Act: -0.0001

Data Index: 445324 (C4 (Web Text))

Max Activating Token Index: 399

Text #2

Max Range: 1.5176. Min Range: -1.5176

Max Act: 1.1725. Min Act: -0.0001

Data Index: 765012 (C4 (Web Text))

Max Activating Token Index: 413

Text #3

Max Range: 1.5176. Min Range: -1.5176

Max Act: 1.2630. Min Act: -0.0001

Data Index: 829275 (C4 (Web Text))

Max Activating Token Index: 621

Text #4

Max Range: 1.5176. Min Range: -1.5176

Max Act: 1.1978. Min Act: -0.0001

Data Index: 97770 (C4 (Web Text))

Max Activating Token Index: 124

Text #5

Max Range: 1.5176. Min Range: -1.5176

Max Act: 1.1550. Min Act: -0.0001

Data Index: 806615 (C4 (Web Text))

Max Activating Token Index: 208

Text #6

Max Range: 1.5176. Min Range: -1.5176

Max Act: 1.1842. Min Act: -0.0001

Data Index: 883776 (C4 (Web Text))

Max Activating Token Index: 428

Text #7

Max Range: 1.5176. Min Range: -1.5176

Max Act: 1.1792. Min Act: -0.0001

Data Index: 1134682 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 1.5176. Min Range: -1.5176

Max Act: 1.0990. Min Act: -0.0001

Data Index: 93497 (C4 (Web Text))

Max Activating Token Index: 340

Text #9

Max Range: 1.5176. Min Range: -1.5176

Max Act: 1.0859. Min Act: -0.0001

Data Index: 1119333 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 1.5176. Min Range: -1.5176

Max Act: 1.0896. Min Act: -0.0001

Data Index: 559716 (C4 (Web Text))

Max Activating Token Index: 565

Text #11

Max Range: 1.5176. Min Range: -1.5176

Max Act: 1.1119. Min Act: -0.0001

Data Index: 1228819 (C4 (Web Text))

Max Activating Token Index: 110

Text #12

Max Range: 1.5176. Min Range: -1.5176

Max Act: 1.0746. Min Act: -0.0001

Data Index: 293040 (C4 (Web Text))

Max Activating Token Index: 252

Text #13

Max Range: 1.5176. Min Range: -1.5176

Max Act: 1.1047. Min Act: -0.0001

Data Index: 479253 (C4 (Web Text))

Max Activating Token Index: 55

Text #14

Max Range: 1.5176. Min Range: -1.5176

Max Act: 1.0333. Min Act: -0.0001

Data Index: 1319127 (C4 (Web Text))

Max Activating Token Index: 584

Text #15

Max Range: 1.5176. Min Range: -1.5176

Max Act: 1.0600. Min Act: -0.0001

Data Index: 120863 (C4 (Web Text))

Max Activating Token Index: 761

Text #16

Max Range: 1.5176. Min Range: -1.5176

Max Act: 1.0861. Min Act: -0.0001

Data Index: 624870 (C4 (Web Text))

Max Activating Token Index: 400

Text #17

Max Range: 1.5176. Min Range: -1.5176

Max Act: 1.0143. Min Act: -0.0001

Data Index: 73046 (C4 (Web Text))

Max Activating Token Index: 383

Text #18

Max Range: 1.5176. Min Range: -1.5176

Max Act: 0.9803. Min Act: -0.0001

Data Index: 44961 (C4 (Web Text))

Max Activating Token Index: 906

Text #19

Max Range: 1.5176. Min Range: -1.5176

Max Act: 0.9664. Min Act: -0.0001

Data Index: 209448 (C4 (Web Text))

Max Activating Token Index: 1000