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

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

Neuron 3214 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: 0.3248. Min Range: -0.3248

Max Act: 0.3248. Min Act: -0.0000

Data Index: 369765 (C4 (Web Text))

Max Activating Token Index: 319

Text #1

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.3054. Min Act: -0.0000

Data Index: 787101 (C4 (Web Text))

Max Activating Token Index: 185

Text #2

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.2370. Min Act: -0.0000

Data Index: 601944 (C4 (Web Text))

Max Activating Token Index: 770

Text #3

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.2559. Min Act: -0.0000

Data Index: 1007083 (C4 (Web Text))

Max Activating Token Index: 887

Text #4

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.2035. Min Act: -0.0000

Data Index: 949025 (C4 (Web Text))

Max Activating Token Index: 178

Text #5

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.1861. Min Act: -0.0000

Data Index: 1070976 (C4 (Web Text))

Max Activating Token Index: 175

Text #6

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.1812. Min Act: -0.0000

Data Index: 474744 (C4 (Web Text))

Max Activating Token Index: 101

Text #7

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.1861. Min Act: -0.0000

Data Index: 914543 (C4 (Web Text))

Max Activating Token Index: 986

Text #8

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.1699. Min Act: -0.0000

Data Index: 468197 (C4 (Web Text))

Max Activating Token Index: 904

Text #9

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.1626. Min Act: -0.0000

Data Index: 196612 (C4 (Web Text))

Max Activating Token Index: 1009

Text #10

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.1672. Min Act: -0.0000

Data Index: 202645 (C4 (Web Text))

Max Activating Token Index: 912

Text #11

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.1737. Min Act: -0.0000

Data Index: 877052 (C4 (Web Text))

Max Activating Token Index: 62

Text #12

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.1666. Min Act: -0.0000

Data Index: 401211 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.1612. Min Act: -0.0000

Data Index: 178824 (C4 (Web Text))

Max Activating Token Index: 337

Text #14

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.1494. Min Act: -0.0000

Data Index: 938987 (C4 (Web Text))

Max Activating Token Index: 960

Text #15

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.1435. Min Act: -0.0000

Data Index: 1307986 (C4 (Web Text))

Max Activating Token Index: 637

Text #16

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.1635. Min Act: -0.0000

Data Index: 312719 (C4 (Web Text))

Max Activating Token Index: 835

Text #17

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.1356. Min Act: -0.0000

Data Index: 1561503 (Python Code)

Max Activating Token Index: 533

Text #18

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.1599. Min Act: -0.0000

Data Index: 1372480 (Python Code)

Max Activating Token Index: 426

Text #19

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.1370. Min Act: -0.0000

Data Index: 675139 (C4 (Web Text))

Max Activating Token Index: 903