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

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

Neuron 5959 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0245. Min Act: -0.0001

Data Index: 586582 (C4 (Web Text))

Max Activating Token Index: 245

Text #1

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0242. Min Act: -0.0001

Data Index: 286131 (C4 (Web Text))

Max Activating Token Index: 636

Text #2

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0245. Min Act: -0.0001

Data Index: 667970 (C4 (Web Text))

Max Activating Token Index: 297

Text #3

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0242. Min Act: -0.0001

Data Index: 909783 (C4 (Web Text))

Max Activating Token Index: 1008

Text #4

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0245. Min Act: -0.0001

Data Index: 533148 (C4 (Web Text))

Max Activating Token Index: 281

Text #5

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0240. Min Act: -0.0001

Data Index: 959848 (C4 (Web Text))

Max Activating Token Index: 838

Text #6

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0242. Min Act: -0.0001

Data Index: 977077 (C4 (Web Text))

Max Activating Token Index: 652

Text #7

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0238. Min Act: -0.0001

Data Index: 899656 (C4 (Web Text))

Max Activating Token Index: 542

Text #8

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0236. Min Act: -0.0001

Data Index: 159532 (C4 (Web Text))

Max Activating Token Index: 157

Text #9

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0235. Min Act: -0.0001

Data Index: 706029 (C4 (Web Text))

Max Activating Token Index: 918

Text #10

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0236. Min Act: -0.0001

Data Index: 1277324 (C4 (Web Text))

Max Activating Token Index: 722

Text #11

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0238. Min Act: -0.0001

Data Index: 326203 (C4 (Web Text))

Max Activating Token Index: 1014

Text #12

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0237. Min Act: -0.0001

Data Index: 1310188 (C4 (Web Text))

Max Activating Token Index: 216

Text #13

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0232. Min Act: -0.0001

Data Index: 932000 (C4 (Web Text))

Max Activating Token Index: 867

Text #14

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0229. Min Act: -0.0001

Data Index: 1044678 (C4 (Web Text))

Max Activating Token Index: 914

Text #15

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0233. Min Act: -0.0001

Data Index: 861807 (C4 (Web Text))

Max Activating Token Index: 889

Text #16

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0228. Min Act: -0.0001

Data Index: 39504 (C4 (Web Text))

Max Activating Token Index: 772

Text #17

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0229. Min Act: -0.0001

Data Index: 943188 (C4 (Web Text))

Max Activating Token Index: 887

Text #18

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0227. Min Act: -0.0001

Data Index: 473966 (C4 (Web Text))

Max Activating Token Index: 471

Text #19

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0225. Min Act: -0.0001

Data Index: 125473 (C4 (Web Text))

Max Activating Token Index: 80