Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2156 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.5169. Min Act: -0.0000

Data Index: 1302834 (C4 (Web Text))

Max Activating Token Index: 420

Text #1

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4268. Min Act: -0.0001

Data Index: 1363726 (Python Code)

Max Activating Token Index: 602

Text #2

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4012. Min Act: -0.0000

Data Index: 1039419 (C4 (Web Text))

Max Activating Token Index: 113

Text #3

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3988. Min Act: -0.0000

Data Index: 348814 (C4 (Web Text))

Max Activating Token Index: 934

Text #4

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3799. Min Act: -0.0001

Data Index: 117396 (C4 (Web Text))

Max Activating Token Index: 1019

Text #5

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3660. Min Act: -0.0001

Data Index: 489459 (C4 (Web Text))

Max Activating Token Index: 1011

Text #6

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3350. Min Act: -0.0001

Data Index: 190390 (C4 (Web Text))

Max Activating Token Index: 918

Text #7

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3377. Min Act: -0.0000

Data Index: 1107362 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3308. Min Act: -0.0001

Data Index: 1554189 (Python Code)

Max Activating Token Index: 462

Text #9

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3326. Min Act: -0.0001

Data Index: 334426 (C4 (Web Text))

Max Activating Token Index: 904

Text #10

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3377. Min Act: -0.0001

Data Index: 1533404 (Python Code)

Max Activating Token Index: 945

Text #11

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3265. Min Act: -0.0001

Data Index: 1347982 (C4 (Web Text))

Max Activating Token Index: 531

Text #12

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3185. Min Act: -0.0001

Data Index: 141795 (C4 (Web Text))

Max Activating Token Index: 557

Text #13

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3254. Min Act: -0.0001

Data Index: 433835 (C4 (Web Text))

Max Activating Token Index: 202

Text #14

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.2986. Min Act: -0.0000

Data Index: 470191 (C4 (Web Text))

Max Activating Token Index: 565

Text #15

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3069. Min Act: -0.0001

Data Index: 131384 (C4 (Web Text))

Max Activating Token Index: 435

Text #16

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3016. Min Act: -0.0001

Data Index: 1289246 (C4 (Web Text))

Max Activating Token Index: 87

Text #17

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3122. Min Act: -0.0001

Data Index: 120751 (C4 (Web Text))

Max Activating Token Index: 306

Text #18

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.2851. Min Act: -0.0001

Data Index: 1048653 (C4 (Web Text))

Max Activating Token Index: 1020

Text #19

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.2812. Min Act: -0.0001

Data Index: 992237 (C4 (Web Text))

Max Activating Token Index: 935