Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 3022 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.8269. Min Act: -0.0001

Data Index: 496203 (C4 (Web Text))

Max Activating Token Index: 731

Text #1

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.7897. Min Act: -0.0001

Data Index: 1345077 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.7339. Min Act: -0.0001

Data Index: 337889 (C4 (Web Text))

Max Activating Token Index: 341

Text #3

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.7828. Min Act: -0.0001

Data Index: 14335 (C4 (Web Text))

Max Activating Token Index: 339

Text #4

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.7177. Min Act: -0.0001

Data Index: 356231 (C4 (Web Text))

Max Activating Token Index: 1013

Text #5

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.7099. Min Act: -0.0001

Data Index: 1019019 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.7195. Min Act: -0.0001

Data Index: 612787 (C4 (Web Text))

Max Activating Token Index: 342

Text #7

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.6746. Min Act: -0.0001

Data Index: 1018182 (C4 (Web Text))

Max Activating Token Index: 252

Text #8

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.6223. Min Act: -0.0001

Data Index: 729893 (C4 (Web Text))

Max Activating Token Index: 37

Text #9

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.6701. Min Act: -0.0001

Data Index: 463131 (C4 (Web Text))

Max Activating Token Index: 420

Text #10

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.5255. Min Act: -0.0001

Data Index: 128644 (C4 (Web Text))

Max Activating Token Index: 624

Text #11

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.6582. Min Act: -0.0001

Data Index: 343100 (C4 (Web Text))

Max Activating Token Index: 985

Text #12

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.6082. Min Act: -0.0001

Data Index: 360055 (C4 (Web Text))

Max Activating Token Index: 700

Text #13

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.6884. Min Act: -0.0001

Data Index: 996964 (C4 (Web Text))

Max Activating Token Index: 757

Text #14

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.6323. Min Act: -0.0001

Data Index: 468282 (C4 (Web Text))

Max Activating Token Index: 199

Text #15

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.6232. Min Act: -0.0001

Data Index: 115070 (C4 (Web Text))

Max Activating Token Index: 450

Text #16

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.6718. Min Act: -0.0001

Data Index: 815904 (C4 (Web Text))

Max Activating Token Index: 683

Text #17

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.5986. Min Act: -0.0001

Data Index: 211914 (C4 (Web Text))

Max Activating Token Index: 668

Text #18

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.6601. Min Act: -0.0001

Data Index: 632583 (C4 (Web Text))

Max Activating Token Index: 953

Text #19

Max Range: 0.8269. Min Range: -0.8269

Max Act: 0.7282. Min Act: -0.0001

Data Index: 257963 (C4 (Web Text))

Max Activating Token Index: 669