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

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

Neuron 3264 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: 2.7883. Min Range: -2.7883

Max Act: 2.7599. Min Act: -0.0000

Data Index: 3825 (C4 (Web Text))

Max Activating Token Index: 769

Text #1

Max Range: 2.7883. Min Range: -2.7883

Max Act: 2.7883. Min Act: -0.0000

Data Index: 341734 (C4 (Web Text))

Max Activating Token Index: 916

Text #2

Max Range: 2.7883. Min Range: -2.7883

Max Act: 2.5168. Min Act: -0.0000

Data Index: 584343 (C4 (Web Text))

Max Activating Token Index: 204

Text #3

Max Range: 2.7883. Min Range: -2.7883

Max Act: 2.5794. Min Act: -0.0000

Data Index: 172212 (C4 (Web Text))

Max Activating Token Index: 247

Text #4

Max Range: 2.7883. Min Range: -2.7883

Max Act: 2.2976. Min Act: -0.0000

Data Index: 1120990 (C4 (Web Text))

Max Activating Token Index: 426

Text #5

Max Range: 2.7883. Min Range: -2.7883

Max Act: 2.1699. Min Act: -0.0000

Data Index: 446408 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 2.7883. Min Range: -2.7883

Max Act: 2.2809. Min Act: -0.0000

Data Index: 993603 (C4 (Web Text))

Max Activating Token Index: 1019

Text #7

Max Range: 2.7883. Min Range: -2.7883

Max Act: 2.2080. Min Act: -0.0000

Data Index: 819502 (C4 (Web Text))

Max Activating Token Index: 850

Text #8

Max Range: 2.7883. Min Range: -2.7883

Max Act: 2.2965. Min Act: -0.0000

Data Index: 464670 (C4 (Web Text))

Max Activating Token Index: 594

Text #9

Max Range: 2.7883. Min Range: -2.7883

Max Act: 2.1475. Min Act: -0.0000

Data Index: 64185 (C4 (Web Text))

Max Activating Token Index: 132

Text #10

Max Range: 2.7883. Min Range: -2.7883

Max Act: 2.1203. Min Act: -0.0000

Data Index: 989951 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 2.7883. Min Range: -2.7883

Max Act: 1.7840. Min Act: -0.0000

Data Index: 1156659 (C4 (Web Text))

Max Activating Token Index: 764

Text #12

Max Range: 2.7883. Min Range: -2.7883

Max Act: 1.9553. Min Act: -0.0000

Data Index: 583585 (C4 (Web Text))

Max Activating Token Index: 63

Text #13

Max Range: 2.7883. Min Range: -2.7883

Max Act: 1.9319. Min Act: -0.0000

Data Index: 838557 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 2.7883. Min Range: -2.7883

Max Act: 1.9254. Min Act: -0.0000

Data Index: 405126 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 2.7883. Min Range: -2.7883

Max Act: 2.1378. Min Act: -0.0000

Data Index: 233089 (C4 (Web Text))

Max Activating Token Index: 856

Text #16

Max Range: 2.7883. Min Range: -2.7883

Max Act: 2.0787. Min Act: -0.0000

Data Index: 130348 (C4 (Web Text))

Max Activating Token Index: 691

Text #17

Max Range: 2.7883. Min Range: -2.7883

Max Act: 1.8759. Min Act: -0.0000

Data Index: 505748 (C4 (Web Text))

Max Activating Token Index: 842

Text #18

Max Range: 2.7883. Min Range: -2.7883

Max Act: 1.8885. Min Act: -0.0000

Data Index: 1316044 (C4 (Web Text))

Max Activating Token Index: 412

Text #19

Max Range: 2.7883. Min Range: -2.7883

Max Act: 1.8647. Min Act: -0.0000

Data Index: 898710 (C4 (Web Text))

Max Activating Token Index: 106