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

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

Neuron 5830 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2805. Min Range: -5.2805

Max Act: 5.2805. Min Act: -0.0000

Data Index: 269443 (C4 (Web Text))

Max Activating Token Index: 171

Text #1

Max Range: 5.2805. Min Range: -5.2805

Max Act: 4.8361. Min Act: -0.0000

Data Index: 867690 (C4 (Web Text))

Max Activating Token Index: 214

Text #2

Max Range: 5.2805. Min Range: -5.2805

Max Act: 4.5901. Min Act: -0.0000

Data Index: 1248507 (C4 (Web Text))

Max Activating Token Index: 192

Text #3

Max Range: 5.2805. Min Range: -5.2805

Max Act: 4.4876. Min Act: -0.0000

Data Index: 673700 (C4 (Web Text))

Max Activating Token Index: 231

Text #4

Max Range: 5.2805. Min Range: -5.2805

Max Act: 4.3793. Min Act: -0.0000

Data Index: 970402 (C4 (Web Text))

Max Activating Token Index: 266

Text #5

Max Range: 5.2805. Min Range: -5.2805

Max Act: 4.0636. Min Act: -0.0000

Data Index: 135677 (C4 (Web Text))

Max Activating Token Index: 162

Text #6

Max Range: 5.2805. Min Range: -5.2805

Max Act: 4.2788. Min Act: -0.0000

Data Index: 357193 (C4 (Web Text))

Max Activating Token Index: 158

Text #7

Max Range: 5.2805. Min Range: -5.2805

Max Act: 3.7108. Min Act: -0.0000

Data Index: 545304 (C4 (Web Text))

Max Activating Token Index: 415

Text #8

Max Range: 5.2805. Min Range: -5.2805

Max Act: 3.6945. Min Act: -0.0000

Data Index: 291242 (C4 (Web Text))

Max Activating Token Index: 426

Text #9

Max Range: 5.2805. Min Range: -5.2805

Max Act: 3.5073. Min Act: -0.0000

Data Index: 182473 (C4 (Web Text))

Max Activating Token Index: 123

Text #10

Max Range: 5.2805. Min Range: -5.2805

Max Act: 3.8172. Min Act: -0.0000

Data Index: 401715 (C4 (Web Text))

Max Activating Token Index: 290

Text #11

Max Range: 5.2805. Min Range: -5.2805

Max Act: 3.5501. Min Act: -0.0000

Data Index: 428483 (C4 (Web Text))

Max Activating Token Index: 428

Text #12

Max Range: 5.2805. Min Range: -5.2805

Max Act: 3.7084. Min Act: -0.0000

Data Index: 339966 (C4 (Web Text))

Max Activating Token Index: 558

Text #13

Max Range: 5.2805. Min Range: -5.2805

Max Act: 3.5318. Min Act: -0.0000

Data Index: 969536 (C4 (Web Text))

Max Activating Token Index: 551

Text #14

Max Range: 5.2805. Min Range: -5.2805

Max Act: 3.4180. Min Act: -0.0000

Data Index: 879731 (C4 (Web Text))

Max Activating Token Index: 605

Text #15

Max Range: 5.2805. Min Range: -5.2805

Max Act: 3.1264. Min Act: -0.0000

Data Index: 658848 (C4 (Web Text))

Max Activating Token Index: 900

Text #16

Max Range: 5.2805. Min Range: -5.2805

Max Act: 3.2351. Min Act: -0.0000

Data Index: 793722 (C4 (Web Text))

Max Activating Token Index: 807

Text #17

Max Range: 5.2805. Min Range: -5.2805

Max Act: 3.3952. Min Act: -0.0000

Data Index: 171676 (C4 (Web Text))

Max Activating Token Index: 616

Text #18

Max Range: 5.2805. Min Range: -5.2805

Max Act: 3.2336. Min Act: -0.0000

Data Index: 931302 (C4 (Web Text))

Max Activating Token Index: 981

Text #19

Max Range: 5.2805. Min Range: -5.2805

Max Act: 3.4086. Min Act: -0.0000

Data Index: 86636 (C4 (Web Text))

Max Activating Token Index: 421