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

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

Neuron 3588 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.2414. Min Act: -0.0000

Data Index: 964967 (C4 (Web Text))

Max Activating Token Index: 282

Text #1

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.2273. Min Act: -0.0000

Data Index: 1259780 (C4 (Web Text))

Max Activating Token Index: 307

Text #2

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.2310. Min Act: -0.0000

Data Index: 142460 (C4 (Web Text))

Max Activating Token Index: 642

Text #3

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.2048. Min Act: -0.0000

Data Index: 327295 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.2175. Min Act: -0.0000

Data Index: 1197010 (C4 (Web Text))

Max Activating Token Index: 981

Text #5

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.2206. Min Act: -0.0000

Data Index: 543399 (C4 (Web Text))

Max Activating Token Index: 494

Text #6

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.2128. Min Act: -0.0000

Data Index: 1077609 (C4 (Web Text))

Max Activating Token Index: 651

Text #7

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.2065. Min Act: -0.0000

Data Index: 278685 (C4 (Web Text))

Max Activating Token Index: 347

Text #8

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.2040. Min Act: -0.0000

Data Index: 157793 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.2034. Min Act: -0.0000

Data Index: 729285 (C4 (Web Text))

Max Activating Token Index: 15

Text #10

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1962. Min Act: -0.0000

Data Index: 738248 (C4 (Web Text))

Max Activating Token Index: 890

Text #11

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.2078. Min Act: -0.0000

Data Index: 344095 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1994. Min Act: -0.0000

Data Index: 1344833 (C4 (Web Text))

Max Activating Token Index: 683

Text #13

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1925. Min Act: -0.0000

Data Index: 567799 (C4 (Web Text))

Max Activating Token Index: 452

Text #14

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1958. Min Act: -0.0000

Data Index: 959694 (C4 (Web Text))

Max Activating Token Index: 18

Text #15

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.2031. Min Act: -0.0000

Data Index: 1358582 (C4 (Web Text))

Max Activating Token Index: 834

Text #16

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1974. Min Act: -0.0000

Data Index: 920141 (C4 (Web Text))

Max Activating Token Index: 22

Text #17

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1894. Min Act: -0.0000

Data Index: 45076 (C4 (Web Text))

Max Activating Token Index: 855

Text #18

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.2021. Min Act: -0.0000

Data Index: 1292605 (C4 (Web Text))

Max Activating Token Index: 629

Text #19

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1871. Min Act: -0.0000

Data Index: 891395 (C4 (Web Text))

Max Activating Token Index: 685