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

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

Neuron 5586 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: 1.5407. Min Range: -1.5407

Max Act: 1.5407. Min Act: -0.0000

Data Index: 1395409 (Python Code)

Max Activating Token Index: 424

Text #1

Max Range: 1.5407. Min Range: -1.5407

Max Act: 1.1710. Min Act: -0.0000

Data Index: 1385508 (Python Code)

Max Activating Token Index: 975

Text #2

Max Range: 1.5407. Min Range: -1.5407

Max Act: 1.0263. Min Act: -0.0000

Data Index: 1129419 (C4 (Web Text))

Max Activating Token Index: 268

Text #3

Max Range: 1.5407. Min Range: -1.5407

Max Act: 1.0023. Min Act: -0.0000

Data Index: 1254177 (C4 (Web Text))

Max Activating Token Index: 965

Text #4

Max Range: 1.5407. Min Range: -1.5407

Max Act: 0.9796. Min Act: -0.0000

Data Index: 936892 (C4 (Web Text))

Max Activating Token Index: 797

Text #5

Max Range: 1.5407. Min Range: -1.5407

Max Act: 0.9020. Min Act: -0.0000

Data Index: 885273 (C4 (Web Text))

Max Activating Token Index: 452

Text #6

Max Range: 1.5407. Min Range: -1.5407

Max Act: 0.8683. Min Act: -0.0000

Data Index: 409931 (C4 (Web Text))

Max Activating Token Index: 784

Text #7

Max Range: 1.5407. Min Range: -1.5407

Max Act: 0.8783. Min Act: 0.0000

Data Index: 889694 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 1.5407. Min Range: -1.5407

Max Act: 0.8223. Min Act: -0.0000

Data Index: 911282 (C4 (Web Text))

Max Activating Token Index: 949

Text #9

Max Range: 1.5407. Min Range: -1.5407

Max Act: 0.7532. Min Act: -0.0000

Data Index: 1573541 (Python Code)

Max Activating Token Index: 266

Text #10

Max Range: 1.5407. Min Range: -1.5407

Max Act: 0.8083. Min Act: -0.0000

Data Index: 213542 (C4 (Web Text))

Max Activating Token Index: 830

Text #11

Max Range: 1.5407. Min Range: -1.5407

Max Act: 0.8020. Min Act: -0.0000

Data Index: 1363047 (Python Code)

Max Activating Token Index: 451

Text #12

Max Range: 1.5407. Min Range: -1.5407

Max Act: 0.8318. Min Act: -0.0000

Data Index: 1289301 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 1.5407. Min Range: -1.5407

Max Act: 0.7705. Min Act: -0.0000

Data Index: 1513190 (Python Code)

Max Activating Token Index: 688

Text #14

Max Range: 1.5407. Min Range: -1.5407

Max Act: 0.8191. Min Act: -0.0000

Data Index: 1189904 (C4 (Web Text))

Max Activating Token Index: 250

Text #15

Max Range: 1.5407. Min Range: -1.5407

Max Act: 0.7906. Min Act: -0.0000

Data Index: 1034480 (C4 (Web Text))

Max Activating Token Index: 444

Text #16

Max Range: 1.5407. Min Range: -1.5407

Max Act: 0.7867. Min Act: -0.0000

Data Index: 897818 (C4 (Web Text))

Max Activating Token Index: 681

Text #17

Max Range: 1.5407. Min Range: -1.5407

Max Act: 0.7402. Min Act: -0.0000

Data Index: 578614 (C4 (Web Text))

Max Activating Token Index: 635

Text #18

Max Range: 1.5407. Min Range: -1.5407

Max Act: 0.7584. Min Act: -0.0000

Data Index: 1183983 (C4 (Web Text))

Max Activating Token Index: 492

Text #19

Max Range: 1.5407. Min Range: -1.5407

Max Act: 0.7604. Min Act: -0.0000

Data Index: 525693 (C4 (Web Text))

Max Activating Token Index: 210