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

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

Neuron 3968 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8847. Min Range: -2.8847

Max Act: 2.8847. Min Act: -0.0000

Data Index: 574093 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 2.8847. Min Range: -2.8847

Max Act: 2.8786. Min Act: -0.0000

Data Index: 827259 (C4 (Web Text))

Max Activating Token Index: 599

Text #2

Max Range: 2.8847. Min Range: -2.8847

Max Act: 2.7623. Min Act: -0.0000

Data Index: 1107578 (C4 (Web Text))

Max Activating Token Index: 445

Text #3

Max Range: 2.8847. Min Range: -2.8847

Max Act: 2.7332. Min Act: -0.0000

Data Index: 121356 (C4 (Web Text))

Max Activating Token Index: 187

Text #4

Max Range: 2.8847. Min Range: -2.8847

Max Act: 2.7027. Min Act: -0.0000

Data Index: 70237 (C4 (Web Text))

Max Activating Token Index: 308

Text #5

Max Range: 2.8847. Min Range: -2.8847

Max Act: 2.4769. Min Act: -0.0000

Data Index: 399013 (C4 (Web Text))

Max Activating Token Index: 314

Text #6

Max Range: 2.8847. Min Range: -2.8847

Max Act: 2.5912. Min Act: -0.0000

Data Index: 1295678 (C4 (Web Text))

Max Activating Token Index: 903

Text #7

Max Range: 2.8847. Min Range: -2.8847

Max Act: 2.4695. Min Act: -0.0000

Data Index: 969332 (C4 (Web Text))

Max Activating Token Index: 986

Text #8

Max Range: 2.8847. Min Range: -2.8847

Max Act: 2.5978. Min Act: -0.0000

Data Index: 1320223 (C4 (Web Text))

Max Activating Token Index: 851

Text #9

Max Range: 2.8847. Min Range: -2.8847

Max Act: 2.4128. Min Act: -0.0000

Data Index: 1356535 (C4 (Web Text))

Max Activating Token Index: 492

Text #10

Max Range: 2.8847. Min Range: -2.8847

Max Act: 2.3431. Min Act: -0.0000

Data Index: 416636 (C4 (Web Text))

Max Activating Token Index: 285

Text #11

Max Range: 2.8847. Min Range: -2.8847

Max Act: 2.1526. Min Act: -0.0000

Data Index: 503816 (C4 (Web Text))

Max Activating Token Index: 277

Text #12

Max Range: 2.8847. Min Range: -2.8847

Max Act: 2.0032. Min Act: -0.0000

Data Index: 1388020 (Python Code)

Max Activating Token Index: 987

Text #13

Max Range: 2.8847. Min Range: -2.8847

Max Act: 2.2216. Min Act: -0.0000

Data Index: 564403 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 2.8847. Min Range: -2.8847

Max Act: 2.0735. Min Act: -0.0000

Data Index: 486938 (C4 (Web Text))

Max Activating Token Index: 679

Text #15

Max Range: 2.8847. Min Range: -2.8847

Max Act: 1.9568. Min Act: -0.0000

Data Index: 1020434 (C4 (Web Text))

Max Activating Token Index: 380

Text #16

Max Range: 2.8847. Min Range: -2.8847

Max Act: 2.0660. Min Act: -0.0000

Data Index: 72850 (C4 (Web Text))

Max Activating Token Index: 877

Text #17

Max Range: 2.8847. Min Range: -2.8847

Max Act: 2.0415. Min Act: -0.0000

Data Index: 1244307 (C4 (Web Text))

Max Activating Token Index: 230

Text #18

Max Range: 2.8847. Min Range: -2.8847

Max Act: 1.9286. Min Act: -0.0000

Data Index: 988557 (C4 (Web Text))

Max Activating Token Index: 156

Text #19

Max Range: 2.8847. Min Range: -2.8847

Max Act: 1.8991. Min Act: -0.0000

Data Index: 1222736 (C4 (Web Text))

Max Activating Token Index: 299