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

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

Neuron 2644 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.6601. Min Act: -0.0000

Data Index: 1031938 (C4 (Web Text))

Max Activating Token Index: 754

Text #1

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.5318. Min Act: -0.0000

Data Index: 1154670 (C4 (Web Text))

Max Activating Token Index: 906

Text #2

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.7165. Min Act: -0.0000

Data Index: 63178 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.7045. Min Act: -0.0000

Data Index: 731543 (C4 (Web Text))

Max Activating Token Index: 494

Text #4

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.6557. Min Act: -0.0000

Data Index: 1222021 (C4 (Web Text))

Max Activating Token Index: 1011

Text #5

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.3510. Min Act: -0.0000

Data Index: 867581 (C4 (Web Text))

Max Activating Token Index: 975

Text #6

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.4455. Min Act: -0.0000

Data Index: 307546 (C4 (Web Text))

Max Activating Token Index: 587

Text #7

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.4180. Min Act: -0.0000

Data Index: 1227286 (C4 (Web Text))

Max Activating Token Index: 397

Text #8

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.4457. Min Act: -0.0000

Data Index: 417810 (C4 (Web Text))

Max Activating Token Index: 317

Text #9

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.3280. Min Act: -0.0000

Data Index: 634631 (C4 (Web Text))

Max Activating Token Index: 123

Text #10

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.3072. Min Act: -0.0000

Data Index: 109107 (C4 (Web Text))

Max Activating Token Index: 917

Text #11

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.2866. Min Act: -0.0000

Data Index: 1082001 (C4 (Web Text))

Max Activating Token Index: 432

Text #12

Max Range: 1.7165. Min Range: -1.7165

Max Act: 0.8360. Min Act: -0.0000

Data Index: 1001966 (C4 (Web Text))

Max Activating Token Index: 742

Text #13

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.2951. Min Act: -0.0000

Data Index: 1127154 (C4 (Web Text))

Max Activating Token Index: 417

Text #14

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.2714. Min Act: -0.0000

Data Index: 39734 (C4 (Web Text))

Max Activating Token Index: 547

Text #15

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.2627. Min Act: -0.0000

Data Index: 513980 (C4 (Web Text))

Max Activating Token Index: 616

Text #16

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.3379. Min Act: -0.0000

Data Index: 189497 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.2279. Min Act: -0.0000

Data Index: 1351222 (C4 (Web Text))

Max Activating Token Index: 374

Text #18

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.2795. Min Act: -0.0000

Data Index: 574515 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.2622. Min Act: -0.0000

Data Index: 514861 (C4 (Web Text))

Max Activating Token Index: 375