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

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

Neuron 3247 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: 1.3249. Min Range: -1.3249

Max Act: 1.3249. Min Act: -0.0000

Data Index: 1027886 (C4 (Web Text))

Max Activating Token Index: 144

Text #1

Max Range: 1.3249. Min Range: -1.3249

Max Act: 1.1954. Min Act: -0.0000

Data Index: 53486 (C4 (Web Text))

Max Activating Token Index: 911

Text #2

Max Range: 1.3249. Min Range: -1.3249

Max Act: 1.1793. Min Act: -0.0000

Data Index: 1308217 (C4 (Web Text))

Max Activating Token Index: 987

Text #3

Max Range: 1.3249. Min Range: -1.3249

Max Act: 1.1586. Min Act: -0.0000

Data Index: 1266382 (C4 (Web Text))

Max Activating Token Index: 551

Text #4

Max Range: 1.3249. Min Range: -1.3249

Max Act: 1.0519. Min Act: -0.0000

Data Index: 1321608 (C4 (Web Text))

Max Activating Token Index: 953

Text #5

Max Range: 1.3249. Min Range: -1.3249

Max Act: 1.0629. Min Act: -0.0000

Data Index: 563766 (C4 (Web Text))

Max Activating Token Index: 436

Text #6

Max Range: 1.3249. Min Range: -1.3249

Max Act: 1.0150. Min Act: -0.0000

Data Index: 1077038 (C4 (Web Text))

Max Activating Token Index: 991

Text #7

Max Range: 1.3249. Min Range: -1.3249

Max Act: 0.9901. Min Act: -0.0000

Data Index: 101513 (C4 (Web Text))

Max Activating Token Index: 984

Text #8

Max Range: 1.3249. Min Range: -1.3249

Max Act: 0.9865. Min Act: -0.0000

Data Index: 538818 (C4 (Web Text))

Max Activating Token Index: 780

Text #9

Max Range: 1.3249. Min Range: -1.3249

Max Act: 0.9443. Min Act: -0.0000

Data Index: 280357 (C4 (Web Text))

Max Activating Token Index: 186

Text #10

Max Range: 1.3249. Min Range: -1.3249

Max Act: 0.9792. Min Act: -0.0000

Data Index: 659848 (C4 (Web Text))

Max Activating Token Index: 656

Text #11

Max Range: 1.3249. Min Range: -1.3249

Max Act: 0.9760. Min Act: -0.0000

Data Index: 489753 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 1.3249. Min Range: -1.3249

Max Act: 1.0055. Min Act: -0.0000

Data Index: 88504 (C4 (Web Text))

Max Activating Token Index: 441

Text #13

Max Range: 1.3249. Min Range: -1.3249

Max Act: 0.9729. Min Act: -0.0000

Data Index: 903266 (C4 (Web Text))

Max Activating Token Index: 862

Text #14

Max Range: 1.3249. Min Range: -1.3249

Max Act: 0.9174. Min Act: -0.0000

Data Index: 133515 (C4 (Web Text))

Max Activating Token Index: 320

Text #15

Max Range: 1.3249. Min Range: -1.3249

Max Act: 0.9260. Min Act: -0.0000

Data Index: 218616 (C4 (Web Text))

Max Activating Token Index: 896

Text #16

Max Range: 1.3249. Min Range: -1.3249

Max Act: 0.8724. Min Act: -0.0000

Data Index: 1321359 (C4 (Web Text))

Max Activating Token Index: 872

Text #17

Max Range: 1.3249. Min Range: -1.3249

Max Act: 0.7772. Min Act: -0.0000

Data Index: 607932 (C4 (Web Text))

Max Activating Token Index: 834

Text #18

Max Range: 1.3249. Min Range: -1.3249

Max Act: 0.8873. Min Act: -0.0000

Data Index: 568747 (C4 (Web Text))

Max Activating Token Index: 449

Text #19

Max Range: 1.3249. Min Range: -1.3249

Max Act: 0.8604. Min Act: -0.0000

Data Index: 758963 (C4 (Web Text))

Max Activating Token Index: 26