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

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

Neuron 1011 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7251. Min Range: -4.7251

Max Act: 4.7251. Min Act: -0.0000

Data Index: 612247 (C4 (Web Text))

Max Activating Token Index: 736

Text #1

Max Range: 4.7251. Min Range: -4.7251

Max Act: 4.1607. Min Act: -0.0000

Data Index: 84152 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 4.7251. Min Range: -4.7251

Max Act: 3.6043. Min Act: -0.0000

Data Index: 1146988 (C4 (Web Text))

Max Activating Token Index: 579

Text #3

Max Range: 4.7251. Min Range: -4.7251

Max Act: 3.5082. Min Act: -0.0001

Data Index: 1195569 (C4 (Web Text))

Max Activating Token Index: 319

Text #4

Max Range: 4.7251. Min Range: -4.7251

Max Act: 3.3798. Min Act: -0.0001

Data Index: 1205269 (C4 (Web Text))

Max Activating Token Index: 574

Text #5

Max Range: 4.7251. Min Range: -4.7251

Max Act: 3.5417. Min Act: -0.0001

Data Index: 151521 (C4 (Web Text))

Max Activating Token Index: 980

Text #6

Max Range: 4.7251. Min Range: -4.7251

Max Act: 3.4767. Min Act: -0.0001

Data Index: 15163 (C4 (Web Text))

Max Activating Token Index: 268

Text #7

Max Range: 4.7251. Min Range: -4.7251

Max Act: 3.4939. Min Act: -0.0001

Data Index: 542846 (C4 (Web Text))

Max Activating Token Index: 446

Text #8

Max Range: 4.7251. Min Range: -4.7251

Max Act: 3.3740. Min Act: -0.0000

Data Index: 1291558 (C4 (Web Text))

Max Activating Token Index: 529

Text #9

Max Range: 4.7251. Min Range: -4.7251

Max Act: 3.4923. Min Act: -0.0001

Data Index: 583700 (C4 (Web Text))

Max Activating Token Index: 826

Text #10

Max Range: 4.7251. Min Range: -4.7251

Max Act: 3.2975. Min Act: -0.0000

Data Index: 1208421 (C4 (Web Text))

Max Activating Token Index: 690

Text #11

Max Range: 4.7251. Min Range: -4.7251

Max Act: 3.0423. Min Act: -0.0001

Data Index: 1019514 (C4 (Web Text))

Max Activating Token Index: 513

Text #12

Max Range: 4.7251. Min Range: -4.7251

Max Act: 3.0480. Min Act: -0.0000

Data Index: 1249210 (C4 (Web Text))

Max Activating Token Index: 323

Text #13

Max Range: 4.7251. Min Range: -4.7251

Max Act: 3.0047. Min Act: -0.0000

Data Index: 1058451 (C4 (Web Text))

Max Activating Token Index: 122

Text #14

Max Range: 4.7251. Min Range: -4.7251

Max Act: 3.0295. Min Act: -0.0001

Data Index: 1200996 (C4 (Web Text))

Max Activating Token Index: 692

Text #15

Max Range: 4.7251. Min Range: -4.7251

Max Act: 2.9303. Min Act: -0.0001

Data Index: 1068300 (C4 (Web Text))

Max Activating Token Index: 805

Text #16

Max Range: 4.7251. Min Range: -4.7251

Max Act: 3.1414. Min Act: -0.0001

Data Index: 1044095 (C4 (Web Text))

Max Activating Token Index: 899

Text #17

Max Range: 4.7251. Min Range: -4.7251

Max Act: 3.0035. Min Act: -0.0000

Data Index: 412265 (C4 (Web Text))

Max Activating Token Index: 414

Text #18

Max Range: 4.7251. Min Range: -4.7251

Max Act: 2.9616. Min Act: -0.0000

Data Index: 54105 (C4 (Web Text))

Max Activating Token Index: 866

Text #19

Max Range: 4.7251. Min Range: -4.7251

Max Act: 2.8179. Min Act: -0.0000

Data Index: 788633 (C4 (Web Text))

Max Activating Token Index: 607