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

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

Neuron 5719 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7215. Min Range: -0.7215

Max Act: 0.7215. Min Act: -0.0000

Data Index: 1363943 (Python Code)

Max Activating Token Index: 302

Text #1

Max Range: 0.7215. Min Range: -0.7215

Max Act: 0.6444. Min Act: -0.0000

Data Index: 868164 (C4 (Web Text))

Max Activating Token Index: 65

Text #2

Max Range: 0.7215. Min Range: -0.7215

Max Act: 0.6598. Min Act: -0.0000

Data Index: 354864 (C4 (Web Text))

Max Activating Token Index: 378

Text #3

Max Range: 0.7215. Min Range: -0.7215

Max Act: 0.6006. Min Act: -0.0000

Data Index: 578861 (C4 (Web Text))

Max Activating Token Index: 452

Text #4

Max Range: 0.7215. Min Range: -0.7215

Max Act: 0.5934. Min Act: -0.0000

Data Index: 867010 (C4 (Web Text))

Max Activating Token Index: 194

Text #5

Max Range: 0.7215. Min Range: -0.7215

Max Act: 0.5450. Min Act: -0.0000

Data Index: 1215655 (C4 (Web Text))

Max Activating Token Index: 810

Text #6

Max Range: 0.7215. Min Range: -0.7215

Max Act: 0.5663. Min Act: -0.0000

Data Index: 1255541 (C4 (Web Text))

Max Activating Token Index: 881

Text #7

Max Range: 0.7215. Min Range: -0.7215

Max Act: 0.5159. Min Act: -0.0000

Data Index: 208584 (C4 (Web Text))

Max Activating Token Index: 843

Text #8

Max Range: 0.7215. Min Range: -0.7215

Max Act: 0.5479. Min Act: -0.0000

Data Index: 991012 (C4 (Web Text))

Max Activating Token Index: 666

Text #9

Max Range: 0.7215. Min Range: -0.7215

Max Act: 0.5339. Min Act: -0.0000

Data Index: 528286 (C4 (Web Text))

Max Activating Token Index: 947

Text #10

Max Range: 0.7215. Min Range: -0.7215

Max Act: 0.5525. Min Act: -0.0000

Data Index: 1191284 (C4 (Web Text))

Max Activating Token Index: 363

Text #11

Max Range: 0.7215. Min Range: -0.7215

Max Act: 0.5141. Min Act: -0.0000

Data Index: 1032721 (C4 (Web Text))

Max Activating Token Index: 835

Text #12

Max Range: 0.7215. Min Range: -0.7215

Max Act: 0.5347. Min Act: -0.0000

Data Index: 1000291 (C4 (Web Text))

Max Activating Token Index: 895

Text #13

Max Range: 0.7215. Min Range: -0.7215

Max Act: 0.5242. Min Act: -0.0000

Data Index: 1130929 (C4 (Web Text))

Max Activating Token Index: 735

Text #14

Max Range: 0.7215. Min Range: -0.7215

Max Act: 0.5391. Min Act: -0.0000

Data Index: 189433 (C4 (Web Text))

Max Activating Token Index: 53

Text #15

Max Range: 0.7215. Min Range: -0.7215

Max Act: 0.5317. Min Act: -0.0000

Data Index: 76421 (C4 (Web Text))

Max Activating Token Index: 368

Text #16

Max Range: 0.7215. Min Range: -0.7215

Max Act: 0.4851. Min Act: -0.0000

Data Index: 540485 (C4 (Web Text))

Max Activating Token Index: 885

Text #17

Max Range: 0.7215. Min Range: -0.7215

Max Act: 0.4812. Min Act: -0.0000

Data Index: 216994 (C4 (Web Text))

Max Activating Token Index: 147

Text #18

Max Range: 0.7215. Min Range: -0.7215

Max Act: 0.4873. Min Act: -0.0000

Data Index: 977179 (C4 (Web Text))

Max Activating Token Index: 544

Text #19

Max Range: 0.7215. Min Range: -0.7215

Max Act: 0.4630. Min Act: -0.0000

Data Index: 1017319 (C4 (Web Text))

Max Activating Token Index: 619