Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 507 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3252. Min Range: -0.3252

Max Act: 0.3252. Min Act: -0.0000

Data Index: 110049 (C4 (Web Text))

Max Activating Token Index: 512

Text #1

Max Range: 0.3252. Min Range: -0.3252

Max Act: 0.2995. Min Act: -0.0000

Data Index: 55699 (C4 (Web Text))

Max Activating Token Index: 298

Text #2

Max Range: 0.3252. Min Range: -0.3252

Max Act: 0.2584. Min Act: -0.0000

Data Index: 1099250 (C4 (Web Text))

Max Activating Token Index: 829

Text #3

Max Range: 0.3252. Min Range: -0.3252

Max Act: 0.2551. Min Act: -0.0000

Data Index: 281086 (C4 (Web Text))

Max Activating Token Index: 532

Text #4

Max Range: 0.3252. Min Range: -0.3252

Max Act: 0.2430. Min Act: -0.0000

Data Index: 467359 (C4 (Web Text))

Max Activating Token Index: 552

Text #5

Max Range: 0.3252. Min Range: -0.3252

Max Act: 0.2344. Min Act: -0.0000

Data Index: 450835 (C4 (Web Text))

Max Activating Token Index: 724

Text #6

Max Range: 0.3252. Min Range: -0.3252

Max Act: 0.2238. Min Act: -0.0000

Data Index: 781320 (C4 (Web Text))

Max Activating Token Index: 827

Text #7

Max Range: 0.3252. Min Range: -0.3252

Max Act: 0.2152. Min Act: -0.0000

Data Index: 1241782 (C4 (Web Text))

Max Activating Token Index: 39

Text #8

Max Range: 0.3252. Min Range: -0.3252

Max Act: 0.2193. Min Act: -0.0000

Data Index: 810880 (C4 (Web Text))

Max Activating Token Index: 368

Text #9

Max Range: 0.3252. Min Range: -0.3252

Max Act: 0.1838. Min Act: -0.0000

Data Index: 1258187 (C4 (Web Text))

Max Activating Token Index: 795

Text #10

Max Range: 0.3252. Min Range: -0.3252

Max Act: 0.1858. Min Act: -0.0000

Data Index: 1183656 (C4 (Web Text))

Max Activating Token Index: 344

Text #11

Max Range: 0.3252. Min Range: -0.3252

Max Act: 0.1883. Min Act: -0.0000

Data Index: 1249658 (C4 (Web Text))

Max Activating Token Index: 156

Text #12

Max Range: 0.3252. Min Range: -0.3252

Max Act: 0.1813. Min Act: -0.0000

Data Index: 28483 (C4 (Web Text))

Max Activating Token Index: 345

Text #13

Max Range: 0.3252. Min Range: -0.3252

Max Act: 0.1752. Min Act: -0.0000

Data Index: 300003 (C4 (Web Text))

Max Activating Token Index: 748

Text #14

Max Range: 0.3252. Min Range: -0.3252

Max Act: 0.1799. Min Act: -0.0000

Data Index: 743006 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 0.3252. Min Range: -0.3252

Max Act: 0.1799. Min Act: -0.0000

Data Index: 1210311 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 0.3252. Min Range: -0.3252

Max Act: 0.1585. Min Act: -0.0000

Data Index: 376901 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 0.3252. Min Range: -0.3252

Max Act: 0.1679. Min Act: -0.0000

Data Index: 1443233 (Python Code)

Max Activating Token Index: 201

Text #18

Max Range: 0.3252. Min Range: -0.3252

Max Act: 0.1557. Min Act: -0.0000

Data Index: 274143 (C4 (Web Text))

Max Activating Token Index: 619

Text #19

Max Range: 0.3252. Min Range: -0.3252

Max Act: 0.1743. Min Act: -0.0000

Data Index: 218200 (C4 (Web Text))

Max Activating Token Index: 555