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

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

Neuron 3000 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6010. Min Range: -4.6010

Max Act: 4.6010. Min Act: -0.0000

Data Index: 212859 (C4 (Web Text))

Max Activating Token Index: 823

Text #1

Max Range: 4.6010. Min Range: -4.6010

Max Act: 3.9465. Min Act: -0.0000

Data Index: 580040 (C4 (Web Text))

Max Activating Token Index: 85

Text #2

Max Range: 4.6010. Min Range: -4.6010

Max Act: 3.7659. Min Act: -0.0000

Data Index: 620624 (C4 (Web Text))

Max Activating Token Index: 493

Text #3

Max Range: 4.6010. Min Range: -4.6010

Max Act: 3.8804. Min Act: -0.0000

Data Index: 401207 (C4 (Web Text))

Max Activating Token Index: 213

Text #4

Max Range: 4.6010. Min Range: -4.6010

Max Act: 3.6807. Min Act: -0.0000

Data Index: 794501 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 4.6010. Min Range: -4.6010

Max Act: 3.6772. Min Act: -0.0000

Data Index: 971530 (C4 (Web Text))

Max Activating Token Index: 328

Text #6

Max Range: 4.6010. Min Range: -4.6010

Max Act: 3.6724. Min Act: -0.0000

Data Index: 1341549 (C4 (Web Text))

Max Activating Token Index: 244

Text #7

Max Range: 4.6010. Min Range: -4.6010

Max Act: 3.6234. Min Act: -0.0000

Data Index: 66738 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 4.6010. Min Range: -4.6010

Max Act: 3.7435. Min Act: -0.0000

Data Index: 613842 (C4 (Web Text))

Max Activating Token Index: 870

Text #9

Max Range: 4.6010. Min Range: -4.6010

Max Act: 3.4828. Min Act: -0.0000

Data Index: 1035240 (C4 (Web Text))

Max Activating Token Index: 387

Text #10

Max Range: 4.6010. Min Range: -4.6010

Max Act: 3.6349. Min Act: -0.0000

Data Index: 1277209 (C4 (Web Text))

Max Activating Token Index: 126

Text #11

Max Range: 4.6010. Min Range: -4.6010

Max Act: 3.1767. Min Act: -0.0000

Data Index: 883089 (C4 (Web Text))

Max Activating Token Index: 239

Text #12

Max Range: 4.6010. Min Range: -4.6010

Max Act: 3.4421. Min Act: -0.0000

Data Index: 886402 (C4 (Web Text))

Max Activating Token Index: 924

Text #13

Max Range: 4.6010. Min Range: -4.6010

Max Act: 2.9371. Min Act: -0.0000

Data Index: 406829 (C4 (Web Text))

Max Activating Token Index: 295

Text #14

Max Range: 4.6010. Min Range: -4.6010

Max Act: 3.2226. Min Act: -0.0000

Data Index: 255328 (C4 (Web Text))

Max Activating Token Index: 951

Text #15

Max Range: 4.6010. Min Range: -4.6010

Max Act: 3.1039. Min Act: -0.0000

Data Index: 1047069 (C4 (Web Text))

Max Activating Token Index: 351

Text #16

Max Range: 4.6010. Min Range: -4.6010

Max Act: 3.2251. Min Act: -0.0000

Data Index: 652494 (C4 (Web Text))

Max Activating Token Index: 994

Text #17

Max Range: 4.6010. Min Range: -4.6010

Max Act: 3.0264. Min Act: -0.0000

Data Index: 582217 (C4 (Web Text))

Max Activating Token Index: 384

Text #18

Max Range: 4.6010. Min Range: -4.6010

Max Act: 3.0414. Min Act: -0.0000

Data Index: 1169813 (C4 (Web Text))

Max Activating Token Index: 308

Text #19

Max Range: 4.6010. Min Range: -4.6010

Max Act: 2.9759. Min Act: -0.0000

Data Index: 922925 (C4 (Web Text))

Max Activating Token Index: 686