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

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

Neuron 5186 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: 2.3377. Min Range: -2.3377

Max Act: 2.3377. Min Act: -0.0000

Data Index: 68042 (C4 (Web Text))

Max Activating Token Index: 792

Text #1

Max Range: 2.3377. Min Range: -2.3377

Max Act: 1.9147. Min Act: -0.0000

Data Index: 614422 (C4 (Web Text))

Max Activating Token Index: 415

Text #2

Max Range: 2.3377. Min Range: -2.3377

Max Act: 1.6076. Min Act: -0.0000

Data Index: 1021400 (C4 (Web Text))

Max Activating Token Index: 448

Text #3

Max Range: 2.3377. Min Range: -2.3377

Max Act: 1.7949. Min Act: -0.0000

Data Index: 214466 (C4 (Web Text))

Max Activating Token Index: 429

Text #4

Max Range: 2.3377. Min Range: -2.3377

Max Act: 1.5533. Min Act: -0.0000

Data Index: 733285 (C4 (Web Text))

Max Activating Token Index: 815

Text #5

Max Range: 2.3377. Min Range: -2.3377

Max Act: 1.5240. Min Act: -0.0000

Data Index: 472539 (C4 (Web Text))

Max Activating Token Index: 32

Text #6

Max Range: 2.3377. Min Range: -2.3377

Max Act: 1.6991. Min Act: -0.0000

Data Index: 1214146 (C4 (Web Text))

Max Activating Token Index: 85

Text #7

Max Range: 2.3377. Min Range: -2.3377

Max Act: 1.3012. Min Act: -0.0000

Data Index: 1040808 (C4 (Web Text))

Max Activating Token Index: 703

Text #8

Max Range: 2.3377. Min Range: -2.3377

Max Act: 1.4545. Min Act: -0.0000

Data Index: 170989 (C4 (Web Text))

Max Activating Token Index: 533

Text #9

Max Range: 2.3377. Min Range: -2.3377

Max Act: 1.4383. Min Act: -0.0000

Data Index: 292896 (C4 (Web Text))

Max Activating Token Index: 276

Text #10

Max Range: 2.3377. Min Range: -2.3377

Max Act: 1.5154. Min Act: -0.0000

Data Index: 999517 (C4 (Web Text))

Max Activating Token Index: 353

Text #11

Max Range: 2.3377. Min Range: -2.3377

Max Act: 1.3295. Min Act: -0.0000

Data Index: 929836 (C4 (Web Text))

Max Activating Token Index: 300

Text #12

Max Range: 2.3377. Min Range: -2.3377

Max Act: 1.4257. Min Act: -0.0000

Data Index: 676545 (C4 (Web Text))

Max Activating Token Index: 657

Text #13

Max Range: 2.3377. Min Range: -2.3377

Max Act: 1.3857. Min Act: -0.0000

Data Index: 734882 (C4 (Web Text))

Max Activating Token Index: 715

Text #14

Max Range: 2.3377. Min Range: -2.3377

Max Act: 1.3508. Min Act: -0.0000

Data Index: 866829 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 2.3377. Min Range: -2.3377

Max Act: 1.3640. Min Act: -0.0000

Data Index: 269277 (C4 (Web Text))

Max Activating Token Index: 933

Text #16

Max Range: 2.3377. Min Range: -2.3377

Max Act: 1.3047. Min Act: -0.0000

Data Index: 349582 (C4 (Web Text))

Max Activating Token Index: 570

Text #17

Max Range: 2.3377. Min Range: -2.3377

Max Act: 1.2212. Min Act: -0.0000

Data Index: 1322405 (C4 (Web Text))

Max Activating Token Index: 669

Text #18

Max Range: 2.3377. Min Range: -2.3377

Max Act: 1.2163. Min Act: -0.0000

Data Index: 432305 (C4 (Web Text))

Max Activating Token Index: 813

Text #19

Max Range: 2.3377. Min Range: -2.3377

Max Act: 1.4849. Min Act: -0.0000

Data Index: 981148 (C4 (Web Text))

Max Activating Token Index: 604