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

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

Neuron 1109 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1143. Min Range: -2.1143

Max Act: 2.0954. Min Act: -0.0000

Data Index: 365847 (C4 (Web Text))

Max Activating Token Index: 631

Text #1

Max Range: 2.1143. Min Range: -2.1143

Max Act: 2.0746. Min Act: -0.0000

Data Index: 813805 (C4 (Web Text))

Max Activating Token Index: 430

Text #2

Max Range: 2.1143. Min Range: -2.1143

Max Act: 2.1143. Min Act: -0.0000

Data Index: 1310252 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 2.1143. Min Range: -2.1143

Max Act: 1.9579. Min Act: -0.0000

Data Index: 977222 (C4 (Web Text))

Max Activating Token Index: 391

Text #4

Max Range: 2.1143. Min Range: -2.1143

Max Act: 1.9091. Min Act: -0.0000

Data Index: 63530 (C4 (Web Text))

Max Activating Token Index: 230

Text #5

Max Range: 2.1143. Min Range: -2.1143

Max Act: 1.8780. Min Act: -0.0000

Data Index: 40017 (C4 (Web Text))

Max Activating Token Index: 621

Text #6

Max Range: 2.1143. Min Range: -2.1143

Max Act: 1.5603. Min Act: -0.0000

Data Index: 516943 (C4 (Web Text))

Max Activating Token Index: 186

Text #7

Max Range: 2.1143. Min Range: -2.1143

Max Act: 1.5604. Min Act: -0.0000

Data Index: 398023 (C4 (Web Text))

Max Activating Token Index: 856

Text #8

Max Range: 2.1143. Min Range: -2.1143

Max Act: 1.5461. Min Act: -0.0000

Data Index: 629825 (C4 (Web Text))

Max Activating Token Index: 949

Text #9

Max Range: 2.1143. Min Range: -2.1143

Max Act: 1.6457. Min Act: -0.0000

Data Index: 606070 (C4 (Web Text))

Max Activating Token Index: 225

Text #10

Max Range: 2.1143. Min Range: -2.1143

Max Act: 1.6183. Min Act: -0.0000

Data Index: 357369 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 2.1143. Min Range: -2.1143

Max Act: 1.7077. Min Act: -0.0000

Data Index: 1314165 (C4 (Web Text))

Max Activating Token Index: 127

Text #12

Max Range: 2.1143. Min Range: -2.1143

Max Act: 1.5671. Min Act: -0.0000

Data Index: 1033325 (C4 (Web Text))

Max Activating Token Index: 188

Text #13

Max Range: 2.1143. Min Range: -2.1143

Max Act: 1.5459. Min Act: -0.0000

Data Index: 1240249 (C4 (Web Text))

Max Activating Token Index: 244

Text #14

Max Range: 2.1143. Min Range: -2.1143

Max Act: 1.5336. Min Act: -0.0000

Data Index: 1273359 (C4 (Web Text))

Max Activating Token Index: 592

Text #15

Max Range: 2.1143. Min Range: -2.1143

Max Act: 1.3292. Min Act: -0.0000

Data Index: 380759 (C4 (Web Text))

Max Activating Token Index: 360

Text #16

Max Range: 2.1143. Min Range: -2.1143

Max Act: 1.4818. Min Act: -0.0000

Data Index: 77537 (C4 (Web Text))

Max Activating Token Index: 341

Text #17

Max Range: 2.1143. Min Range: -2.1143

Max Act: 1.5543. Min Act: -0.0000

Data Index: 1131940 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 2.1143. Min Range: -2.1143

Max Act: 1.5322. Min Act: -0.0000

Data Index: 560469 (C4 (Web Text))

Max Activating Token Index: 915

Text #19

Max Range: 2.1143. Min Range: -2.1143

Max Act: 1.2805. Min Act: -0.0000

Data Index: 132544 (C4 (Web Text))

Max Activating Token Index: 980