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

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

Neuron 86 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: 0.2959. Min Range: -0.2959

Max Act: 0.2959. Min Act: -0.0002

Data Index: 963215 (C4 (Web Text))

Max Activating Token Index: 258

Text #1

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2261. Min Act: -0.0002

Data Index: 402163 (C4 (Web Text))

Max Activating Token Index: 269

Text #2

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2676. Min Act: -0.0002

Data Index: 791066 (C4 (Web Text))

Max Activating Token Index: 506

Text #3

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2328. Min Act: -0.0002

Data Index: 1152461 (C4 (Web Text))

Max Activating Token Index: 162

Text #4

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2114. Min Act: -0.0002

Data Index: 1017045 (C4 (Web Text))

Max Activating Token Index: 210

Text #5

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2441. Min Act: -0.0002

Data Index: 59114 (C4 (Web Text))

Max Activating Token Index: 261

Text #6

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2357. Min Act: -0.0002

Data Index: 829251 (C4 (Web Text))

Max Activating Token Index: 1019

Text #7

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2256. Min Act: -0.0002

Data Index: 1338013 (C4 (Web Text))

Max Activating Token Index: 240

Text #8

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2575. Min Act: -0.0002

Data Index: 1120432 (C4 (Web Text))

Max Activating Token Index: 292

Text #9

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2477. Min Act: -0.0002

Data Index: 274137 (C4 (Web Text))

Max Activating Token Index: 95

Text #10

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2466. Min Act: -0.0002

Data Index: 1032445 (C4 (Web Text))

Max Activating Token Index: 683

Text #11

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2318. Min Act: -0.0002

Data Index: 638483 (C4 (Web Text))

Max Activating Token Index: 163

Text #12

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2484. Min Act: -0.0002

Data Index: 877553 (C4 (Web Text))

Max Activating Token Index: 320

Text #13

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2306. Min Act: -0.0002

Data Index: 730905 (C4 (Web Text))

Max Activating Token Index: 215

Text #14

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2395. Min Act: -0.0002

Data Index: 560939 (C4 (Web Text))

Max Activating Token Index: 29

Text #15

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2575. Min Act: -0.0002

Data Index: 339751 (C4 (Web Text))

Max Activating Token Index: 128

Text #16

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2293. Min Act: -0.0002

Data Index: 1259473 (C4 (Web Text))

Max Activating Token Index: 386

Text #17

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2447. Min Act: -0.0002

Data Index: 636848 (C4 (Web Text))

Max Activating Token Index: 80

Text #18

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2367. Min Act: -0.0002

Data Index: 927151 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2452. Min Act: -0.0002

Data Index: 955784 (C4 (Web Text))

Max Activating Token Index: 786