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

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

Neuron 2236 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.8527. Min Act: -0.0000

Data Index: 457443 (C4 (Web Text))

Max Activating Token Index: 481

Text #1

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.7232. Min Act: -0.0000

Data Index: 1152720 (C4 (Web Text))

Max Activating Token Index: 1003

Text #2

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.4172. Min Act: 0.0000

Data Index: 763051 (C4 (Web Text))

Max Activating Token Index: 374

Text #3

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.3826. Min Act: 0.0000

Data Index: 371369 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.3832. Min Act: -0.0000

Data Index: 566154 (C4 (Web Text))

Max Activating Token Index: 35

Text #5

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.3796. Min Act: -0.0000

Data Index: 800139 (C4 (Web Text))

Max Activating Token Index: 581

Text #6

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.3621. Min Act: -0.0000

Data Index: 183864 (C4 (Web Text))

Max Activating Token Index: 273

Text #7

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.3737. Min Act: 0.0000

Data Index: 258265 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.3489. Min Act: -0.0000

Data Index: 1291995 (C4 (Web Text))

Max Activating Token Index: 714

Text #9

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.3597. Min Act: -0.0000

Data Index: 62239 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.3219. Min Act: -0.0000

Data Index: 492668 (C4 (Web Text))

Max Activating Token Index: 379

Text #11

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.3480. Min Act: 0.0000

Data Index: 464192 (C4 (Web Text))

Max Activating Token Index: 192

Text #12

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.3696. Min Act: -0.0000

Data Index: 489772 (C4 (Web Text))

Max Activating Token Index: 672

Text #13

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.3572. Min Act: -0.0000

Data Index: 806201 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.3435. Min Act: -0.0000

Data Index: 187099 (C4 (Web Text))

Max Activating Token Index: 547

Text #15

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.3330. Min Act: -0.0000

Data Index: 749365 (C4 (Web Text))

Max Activating Token Index: 922

Text #16

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.3258. Min Act: -0.0000

Data Index: 481966 (C4 (Web Text))

Max Activating Token Index: 467

Text #17

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.3200. Min Act: -0.0000

Data Index: 234721 (C4 (Web Text))

Max Activating Token Index: 574

Text #18

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.3201. Min Act: -0.0000

Data Index: 152914 (C4 (Web Text))

Max Activating Token Index: 911

Text #19

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.3104. Min Act: -0.0000

Data Index: 948055 (C4 (Web Text))

Max Activating Token Index: 653