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

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

Neuron 1068 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6355. Min Range: -1.6355

Max Act: 1.6355. Min Act: -0.0000

Data Index: 926300 (C4 (Web Text))

Max Activating Token Index: 93

Text #1

Max Range: 1.6355. Min Range: -1.6355

Max Act: 1.5021. Min Act: -0.0000

Data Index: 350171 (C4 (Web Text))

Max Activating Token Index: 1002

Text #2

Max Range: 1.6355. Min Range: -1.6355

Max Act: 1.4421. Min Act: -0.0000

Data Index: 962750 (C4 (Web Text))

Max Activating Token Index: 578

Text #3

Max Range: 1.6355. Min Range: -1.6355

Max Act: 1.4377. Min Act: -0.0000

Data Index: 1214589 (C4 (Web Text))

Max Activating Token Index: 949

Text #4

Max Range: 1.6355. Min Range: -1.6355

Max Act: 1.4542. Min Act: -0.0000

Data Index: 415339 (C4 (Web Text))

Max Activating Token Index: 572

Text #5

Max Range: 1.6355. Min Range: -1.6355

Max Act: 1.2095. Min Act: -0.0000

Data Index: 1307414 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 1.6355. Min Range: -1.6355

Max Act: 1.2713. Min Act: -0.0000

Data Index: 184067 (C4 (Web Text))

Max Activating Token Index: 168

Text #7

Max Range: 1.6355. Min Range: -1.6355

Max Act: 1.1358. Min Act: -0.0000

Data Index: 179757 (C4 (Web Text))

Max Activating Token Index: 130

Text #8

Max Range: 1.6355. Min Range: -1.6355

Max Act: 1.1512. Min Act: -0.0000

Data Index: 1299933 (C4 (Web Text))

Max Activating Token Index: 467

Text #9

Max Range: 1.6355. Min Range: -1.6355

Max Act: 1.0472. Min Act: -0.0000

Data Index: 372075 (C4 (Web Text))

Max Activating Token Index: 756

Text #10

Max Range: 1.6355. Min Range: -1.6355

Max Act: 0.9818. Min Act: -0.0000

Data Index: 969261 (C4 (Web Text))

Max Activating Token Index: 151

Text #11

Max Range: 1.6355. Min Range: -1.6355

Max Act: 1.0959. Min Act: -0.0000

Data Index: 994463 (C4 (Web Text))

Max Activating Token Index: 694

Text #12

Max Range: 1.6355. Min Range: -1.6355

Max Act: 1.0728. Min Act: -0.0000

Data Index: 507720 (C4 (Web Text))

Max Activating Token Index: 365

Text #13

Max Range: 1.6355. Min Range: -1.6355

Max Act: 1.0185. Min Act: -0.0000

Data Index: 195020 (C4 (Web Text))

Max Activating Token Index: 236

Text #14

Max Range: 1.6355. Min Range: -1.6355

Max Act: 1.0180. Min Act: -0.0000

Data Index: 1187876 (C4 (Web Text))

Max Activating Token Index: 695

Text #15

Max Range: 1.6355. Min Range: -1.6355

Max Act: 1.0241. Min Act: -0.0000

Data Index: 278002 (C4 (Web Text))

Max Activating Token Index: 851

Text #16

Max Range: 1.6355. Min Range: -1.6355

Max Act: 1.0226. Min Act: -0.0000

Data Index: 299589 (C4 (Web Text))

Max Activating Token Index: 893

Text #17

Max Range: 1.6355. Min Range: -1.6355

Max Act: 0.9646. Min Act: -0.0000

Data Index: 1226270 (C4 (Web Text))

Max Activating Token Index: 488

Text #18

Max Range: 1.6355. Min Range: -1.6355

Max Act: 1.0225. Min Act: -0.0000

Data Index: 637026 (C4 (Web Text))

Max Activating Token Index: 275

Text #19

Max Range: 1.6355. Min Range: -1.6355

Max Act: 0.9422. Min Act: -0.0000

Data Index: 1229091 (C4 (Web Text))

Max Activating Token Index: 11