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

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

Neuron 3191 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: 0.5737. Min Range: -0.5737

Max Act: 0.5737. Min Act: -0.0000

Data Index: 679521 (C4 (Web Text))

Max Activating Token Index: 185

Text #1

Max Range: 0.5737. Min Range: -0.5737

Max Act: 0.4351. Min Act: -0.0000

Data Index: 1261277 (C4 (Web Text))

Max Activating Token Index: 954

Text #2

Max Range: 0.5737. Min Range: -0.5737

Max Act: 0.3293. Min Act: -0.0000

Data Index: 1199284 (C4 (Web Text))

Max Activating Token Index: 517

Text #3

Max Range: 0.5737. Min Range: -0.5737

Max Act: 0.2544. Min Act: -0.0000

Data Index: 1162557 (C4 (Web Text))

Max Activating Token Index: 568

Text #4

Max Range: 0.5737. Min Range: -0.5737

Max Act: 0.2667. Min Act: -0.0000

Data Index: 587934 (C4 (Web Text))

Max Activating Token Index: 969

Text #5

Max Range: 0.5737. Min Range: -0.5737

Max Act: 0.2391. Min Act: -0.0000

Data Index: 933187 (C4 (Web Text))

Max Activating Token Index: 886

Text #6

Max Range: 0.5737. Min Range: -0.5737

Max Act: 0.2139. Min Act: -0.0000

Data Index: 1643274 (Python Code)

Max Activating Token Index: 991

Text #7

Max Range: 0.5737. Min Range: -0.5737

Max Act: 0.2849. Min Act: -0.0000

Data Index: 71550 (C4 (Web Text))

Max Activating Token Index: 187

Text #8

Max Range: 0.5737. Min Range: -0.5737

Max Act: 0.1837. Min Act: -0.0000

Data Index: 1553494 (Python Code)

Max Activating Token Index: 494

Text #9

Max Range: 0.5737. Min Range: -0.5737

Max Act: 0.1974. Min Act: -0.0000

Data Index: 1583204 (Python Code)

Max Activating Token Index: 264

Text #10

Max Range: 0.5737. Min Range: -0.5737

Max Act: 0.2023. Min Act: -0.0000

Data Index: 931058 (C4 (Web Text))

Max Activating Token Index: 549

Text #11

Max Range: 0.5737. Min Range: -0.5737

Max Act: 0.2392. Min Act: -0.0000

Data Index: 790889 (C4 (Web Text))

Max Activating Token Index: 879

Text #12

Max Range: 0.5737. Min Range: -0.5737

Max Act: 0.2057. Min Act: -0.0000

Data Index: 680543 (C4 (Web Text))

Max Activating Token Index: 829

Text #13

Max Range: 0.5737. Min Range: -0.5737

Max Act: 0.1952. Min Act: -0.0000

Data Index: 810709 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 0.5737. Min Range: -0.5737

Max Act: 0.2154. Min Act: -0.0000

Data Index: 1490637 (Python Code)

Max Activating Token Index: 214

Text #15

Max Range: 0.5737. Min Range: -0.5737

Max Act: 0.1842. Min Act: -0.0000

Data Index: 557342 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 0.5737. Min Range: -0.5737

Max Act: 0.1710. Min Act: -0.0000

Data Index: 611434 (C4 (Web Text))

Max Activating Token Index: 203

Text #17

Max Range: 0.5737. Min Range: -0.5737

Max Act: 0.2038. Min Act: -0.0000

Data Index: 906998 (C4 (Web Text))

Max Activating Token Index: 900

Text #18

Max Range: 0.5737. Min Range: -0.5737

Max Act: 0.1787. Min Act: -0.0000

Data Index: 652946 (C4 (Web Text))

Max Activating Token Index: 212

Text #19

Max Range: 0.5737. Min Range: -0.5737

Max Act: 0.1761. Min Act: -0.0000

Data Index: 205049 (C4 (Web Text))

Max Activating Token Index: 201