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

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

Neuron 4240 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0036. Min Range: -1.0036

Max Act: 1.0036. Min Act: -0.0000

Data Index: 38375 (C4 (Web Text))

Max Activating Token Index: 917

Text #1

Max Range: 1.0036. Min Range: -1.0036

Max Act: 0.9759. Min Act: -0.0000

Data Index: 693318 (C4 (Web Text))

Max Activating Token Index: 225

Text #2

Max Range: 1.0036. Min Range: -1.0036

Max Act: 0.8251. Min Act: -0.0000

Data Index: 1163520 (C4 (Web Text))

Max Activating Token Index: 336

Text #3

Max Range: 1.0036. Min Range: -1.0036

Max Act: 0.8210. Min Act: -0.0000

Data Index: 1003490 (C4 (Web Text))

Max Activating Token Index: 786

Text #4

Max Range: 1.0036. Min Range: -1.0036

Max Act: 0.8702. Min Act: -0.0000

Data Index: 749805 (C4 (Web Text))

Max Activating Token Index: 361

Text #5

Max Range: 1.0036. Min Range: -1.0036

Max Act: 0.8961. Min Act: -0.0000

Data Index: 1129183 (C4 (Web Text))

Max Activating Token Index: 238

Text #6

Max Range: 1.0036. Min Range: -1.0036

Max Act: 0.7804. Min Act: -0.0000

Data Index: 878987 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 1.0036. Min Range: -1.0036

Max Act: 0.7579. Min Act: -0.0000

Data Index: 352612 (C4 (Web Text))

Max Activating Token Index: 439

Text #8

Max Range: 1.0036. Min Range: -1.0036

Max Act: 0.7381. Min Act: -0.0000

Data Index: 1113069 (C4 (Web Text))

Max Activating Token Index: 759

Text #9

Max Range: 1.0036. Min Range: -1.0036

Max Act: 0.7562. Min Act: -0.0000

Data Index: 535086 (C4 (Web Text))

Max Activating Token Index: 480

Text #10

Max Range: 1.0036. Min Range: -1.0036

Max Act: 0.6624. Min Act: -0.0000

Data Index: 1009814 (C4 (Web Text))

Max Activating Token Index: 573

Text #11

Max Range: 1.0036. Min Range: -1.0036

Max Act: 0.6385. Min Act: -0.0000

Data Index: 356780 (C4 (Web Text))

Max Activating Token Index: 588

Text #12

Max Range: 1.0036. Min Range: -1.0036

Max Act: 0.5916. Min Act: -0.0000

Data Index: 458142 (C4 (Web Text))

Max Activating Token Index: 448

Text #13

Max Range: 1.0036. Min Range: -1.0036

Max Act: 0.6271. Min Act: -0.0000

Data Index: 821948 (C4 (Web Text))

Max Activating Token Index: 339

Text #14

Max Range: 1.0036. Min Range: -1.0036

Max Act: 0.6252. Min Act: -0.0000

Data Index: 255746 (C4 (Web Text))

Max Activating Token Index: 357

Text #15

Max Range: 1.0036. Min Range: -1.0036

Max Act: 0.5975. Min Act: -0.0000

Data Index: 598186 (C4 (Web Text))

Max Activating Token Index: 861

Text #16

Max Range: 1.0036. Min Range: -1.0036

Max Act: 0.6735. Min Act: -0.0000

Data Index: 227094 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 1.0036. Min Range: -1.0036

Max Act: 0.6045. Min Act: -0.0000

Data Index: 583463 (C4 (Web Text))

Max Activating Token Index: 925

Text #18

Max Range: 1.0036. Min Range: -1.0036

Max Act: 0.6154. Min Act: -0.0001

Data Index: 68401 (C4 (Web Text))

Max Activating Token Index: 999

Text #19

Max Range: 1.0036. Min Range: -1.0036

Max Act: 0.6274. Min Act: -0.0000

Data Index: 565957 (C4 (Web Text))

Max Activating Token Index: 24