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

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

Neuron 989 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3325. Min Range: -0.3325

Max Act: 0.3325. Min Act: -0.0000

Data Index: 1421160 (Python Code)

Max Activating Token Index: 391

Text #1

Max Range: 0.3325. Min Range: -0.3325

Max Act: 0.3001. Min Act: -0.0000

Data Index: 1613986 (Python Code)

Max Activating Token Index: 953

Text #2

Max Range: 0.3325. Min Range: -0.3325

Max Act: 0.2913. Min Act: -0.0000

Data Index: 1070846 (C4 (Web Text))

Max Activating Token Index: 650

Text #3

Max Range: 0.3325. Min Range: -0.3325

Max Act: 0.2815. Min Act: -0.0000

Data Index: 711019 (C4 (Web Text))

Max Activating Token Index: 757

Text #4

Max Range: 0.3325. Min Range: -0.3325

Max Act: 0.2754. Min Act: -0.0000

Data Index: 1642200 (Python Code)

Max Activating Token Index: 505

Text #5

Max Range: 0.3325. Min Range: -0.3325

Max Act: 0.2635. Min Act: -0.0000

Data Index: 479171 (C4 (Web Text))

Max Activating Token Index: 367

Text #6

Max Range: 0.3325. Min Range: -0.3325

Max Act: 0.2324. Min Act: -0.0000

Data Index: 1117668 (C4 (Web Text))

Max Activating Token Index: 548

Text #7

Max Range: 0.3325. Min Range: -0.3325

Max Act: 0.2339. Min Act: -0.0000

Data Index: 223525 (C4 (Web Text))

Max Activating Token Index: 447

Text #8

Max Range: 0.3325. Min Range: -0.3325

Max Act: 0.2220. Min Act: -0.0000

Data Index: 1267576 (C4 (Web Text))

Max Activating Token Index: 792

Text #9

Max Range: 0.3325. Min Range: -0.3325

Max Act: 0.2189. Min Act: -0.0000

Data Index: 57851 (C4 (Web Text))

Max Activating Token Index: 53

Text #10

Max Range: 0.3325. Min Range: -0.3325

Max Act: 0.2143. Min Act: -0.0000

Data Index: 1241369 (C4 (Web Text))

Max Activating Token Index: 963

Text #11

Max Range: 0.3325. Min Range: -0.3325

Max Act: 0.2005. Min Act: -0.0000

Data Index: 1452298 (Python Code)

Max Activating Token Index: 624

Text #12

Max Range: 0.3325. Min Range: -0.3325

Max Act: 0.1960. Min Act: -0.0000

Data Index: 348622 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 0.3325. Min Range: -0.3325

Max Act: 0.1990. Min Act: -0.0000

Data Index: 300009 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 0.3325. Min Range: -0.3325

Max Act: 0.1973. Min Act: -0.0000

Data Index: 847169 (C4 (Web Text))

Max Activating Token Index: 140

Text #15

Max Range: 0.3325. Min Range: -0.3325

Max Act: 0.2048. Min Act: 0.0000

Data Index: 185388 (C4 (Web Text))

Max Activating Token Index: 118

Text #16

Max Range: 0.3325. Min Range: -0.3325

Max Act: 0.1889. Min Act: -0.0000

Data Index: 1531028 (Python Code)

Max Activating Token Index: 273

Text #17

Max Range: 0.3325. Min Range: -0.3325

Max Act: 0.1885. Min Act: 0.0000

Data Index: 295770 (C4 (Web Text))

Max Activating Token Index: 141

Text #18

Max Range: 0.3325. Min Range: -0.3325

Max Act: 0.1829. Min Act: -0.0000

Data Index: 778662 (C4 (Web Text))

Max Activating Token Index: 368

Text #19

Max Range: 0.3325. Min Range: -0.3325

Max Act: 0.1899. Min Act: -0.0000

Data Index: 658278 (C4 (Web Text))

Max Activating Token Index: 513