Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4039 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9582. Min Range: -0.9582

Max Act: 0.9582. Min Act: -0.0001

Data Index: 907512 (C4 (Web Text))

Max Activating Token Index: 274

Text #1

Max Range: 0.9582. Min Range: -0.9582

Max Act: 0.8506. Min Act: -0.0000

Data Index: 330469 (C4 (Web Text))

Max Activating Token Index: 231

Text #2

Max Range: 0.9582. Min Range: -0.9582

Max Act: 0.7145. Min Act: -0.0000

Data Index: 443859 (C4 (Web Text))

Max Activating Token Index: 795

Text #3

Max Range: 0.9582. Min Range: -0.9582

Max Act: 0.7158. Min Act: -0.0001

Data Index: 82193 (C4 (Web Text))

Max Activating Token Index: 374

Text #4

Max Range: 0.9582. Min Range: -0.9582

Max Act: 0.6884. Min Act: -0.0001

Data Index: 452617 (C4 (Web Text))

Max Activating Token Index: 724

Text #5

Max Range: 0.9582. Min Range: -0.9582

Max Act: 0.6834. Min Act: -0.0000

Data Index: 239524 (C4 (Web Text))

Max Activating Token Index: 95

Text #6

Max Range: 0.9582. Min Range: -0.9582

Max Act: 0.6892. Min Act: -0.0000

Data Index: 357893 (C4 (Web Text))

Max Activating Token Index: 867

Text #7

Max Range: 0.9582. Min Range: -0.9582

Max Act: 0.6468. Min Act: -0.0000

Data Index: 55862 (C4 (Web Text))

Max Activating Token Index: 285

Text #8

Max Range: 0.9582. Min Range: -0.9582

Max Act: 0.6497. Min Act: -0.0000

Data Index: 609966 (C4 (Web Text))

Max Activating Token Index: 441

Text #9

Max Range: 0.9582. Min Range: -0.9582

Max Act: 0.6247. Min Act: -0.0000

Data Index: 298056 (C4 (Web Text))

Max Activating Token Index: 390

Text #10

Max Range: 0.9582. Min Range: -0.9582

Max Act: 0.6635. Min Act: -0.0001

Data Index: 139662 (C4 (Web Text))

Max Activating Token Index: 496

Text #11

Max Range: 0.9582. Min Range: -0.9582

Max Act: 0.5877. Min Act: -0.0001

Data Index: 675210 (C4 (Web Text))

Max Activating Token Index: 530

Text #12

Max Range: 0.9582. Min Range: -0.9582

Max Act: 0.6120. Min Act: -0.0000

Data Index: 1191239 (C4 (Web Text))

Max Activating Token Index: 966

Text #13

Max Range: 0.9582. Min Range: -0.9582

Max Act: 0.6720. Min Act: -0.0000

Data Index: 259581 (C4 (Web Text))

Max Activating Token Index: 1007

Text #14

Max Range: 0.9582. Min Range: -0.9582

Max Act: 0.6032. Min Act: -0.0000

Data Index: 889216 (C4 (Web Text))

Max Activating Token Index: 191

Text #15

Max Range: 0.9582. Min Range: -0.9582

Max Act: 0.5965. Min Act: -0.0001

Data Index: 619071 (C4 (Web Text))

Max Activating Token Index: 326

Text #16

Max Range: 0.9582. Min Range: -0.9582

Max Act: 0.5884. Min Act: -0.0000

Data Index: 139165 (C4 (Web Text))

Max Activating Token Index: 587

Text #17

Max Range: 0.9582. Min Range: -0.9582

Max Act: 0.6072. Min Act: -0.0001

Data Index: 1189679 (C4 (Web Text))

Max Activating Token Index: 585

Text #18

Max Range: 0.9582. Min Range: -0.9582

Max Act: 0.5723. Min Act: -0.0000

Data Index: 479997 (C4 (Web Text))

Max Activating Token Index: 82

Text #19

Max Range: 0.9582. Min Range: -0.9582

Max Act: 0.5898. Min Act: -0.0000

Data Index: 252726 (C4 (Web Text))

Max Activating Token Index: 305