Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3028 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1414. Min Act: -0.0002

Data Index: 647858 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1084. Min Act: -0.0002

Data Index: 793309 (C4 (Web Text))

Max Activating Token Index: 233

Text #2

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1420. Min Act: -0.0002

Data Index: 508807 (C4 (Web Text))

Max Activating Token Index: 811

Text #3

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1223. Min Act: -0.0002

Data Index: 1195138 (C4 (Web Text))

Max Activating Token Index: 65

Text #4

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1273. Min Act: -0.0002

Data Index: 270792 (C4 (Web Text))

Max Activating Token Index: 116

Text #5

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1207. Min Act: -0.0002

Data Index: 560288 (C4 (Web Text))

Max Activating Token Index: 443

Text #6

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1254. Min Act: -0.0002

Data Index: 626492 (C4 (Web Text))

Max Activating Token Index: 456

Text #7

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1242. Min Act: -0.0002

Data Index: 815139 (C4 (Web Text))

Max Activating Token Index: 730

Text #8

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1228. Min Act: -0.0002

Data Index: 440644 (C4 (Web Text))

Max Activating Token Index: 32

Text #9

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1313. Min Act: -0.0002

Data Index: 177205 (C4 (Web Text))

Max Activating Token Index: 318

Text #10

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1006. Min Act: -0.0002

Data Index: 1000842 (C4 (Web Text))

Max Activating Token Index: 528

Text #11

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1213. Min Act: -0.0002

Data Index: 566180 (C4 (Web Text))

Max Activating Token Index: 139

Text #12

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1117. Min Act: -0.0002

Data Index: 434253 (C4 (Web Text))

Max Activating Token Index: 267

Text #13

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1200. Min Act: -0.0002

Data Index: 52385 (C4 (Web Text))

Max Activating Token Index: 341

Text #14

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1055. Min Act: -0.0002

Data Index: 995294 (C4 (Web Text))

Max Activating Token Index: 245

Text #15

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1013. Min Act: -0.0002

Data Index: 1254386 (C4 (Web Text))

Max Activating Token Index: 503

Text #16

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1142. Min Act: -0.0002

Data Index: 1205736 (C4 (Web Text))

Max Activating Token Index: 972

Text #17

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1068. Min Act: -0.0002

Data Index: 420907 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1059. Min Act: -0.0002

Data Index: 130594 (C4 (Web Text))

Max Activating Token Index: 202

Text #19

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1025. Min Act: -0.0002

Data Index: 1357379 (C4 (Web Text))

Max Activating Token Index: 53