Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 245 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5357. Min Range: -1.5357

Max Act: 1.5357. Min Act: -0.0002

Data Index: 759920 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 1.5357. Min Range: -1.5357

Max Act: 1.4431. Min Act: -0.0002

Data Index: 341549 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 1.5357. Min Range: -1.5357

Max Act: 1.3223. Min Act: -0.0002

Data Index: 786356 (C4 (Web Text))

Max Activating Token Index: 90

Text #3

Max Range: 1.5357. Min Range: -1.5357

Max Act: 1.2351. Min Act: -0.0002

Data Index: 31123 (C4 (Web Text))

Max Activating Token Index: 90

Text #4

Max Range: 1.5357. Min Range: -1.5357

Max Act: 1.0715. Min Act: -0.0002

Data Index: 314658 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 1.5357. Min Range: -1.5357

Max Act: 1.1015. Min Act: -0.0002

Data Index: 1240303 (C4 (Web Text))

Max Activating Token Index: 105

Text #6

Max Range: 1.5357. Min Range: -1.5357

Max Act: 1.1492. Min Act: -0.0002

Data Index: 303994 (C4 (Web Text))

Max Activating Token Index: 328

Text #7

Max Range: 1.5357. Min Range: -1.5357

Max Act: 1.0578. Min Act: -0.0002

Data Index: 972804 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 1.5357. Min Range: -1.5357

Max Act: 1.2389. Min Act: -0.0002

Data Index: 121666 (C4 (Web Text))

Max Activating Token Index: 245

Text #9

Max Range: 1.5357. Min Range: -1.5357

Max Act: 0.9370. Min Act: -0.0002

Data Index: 788001 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 1.5357. Min Range: -1.5357

Max Act: 0.9807. Min Act: -0.0002

Data Index: 517171 (C4 (Web Text))

Max Activating Token Index: 950

Text #11

Max Range: 1.5357. Min Range: -1.5357

Max Act: 1.0351. Min Act: -0.0002

Data Index: 426485 (C4 (Web Text))

Max Activating Token Index: 8

Text #12

Max Range: 1.5357. Min Range: -1.5357

Max Act: 0.9608. Min Act: -0.0002

Data Index: 32324 (C4 (Web Text))

Max Activating Token Index: 236

Text #13

Max Range: 1.5357. Min Range: -1.5357

Max Act: 1.0594. Min Act: -0.0002

Data Index: 79456 (C4 (Web Text))

Max Activating Token Index: 15

Text #14

Max Range: 1.5357. Min Range: -1.5357

Max Act: 0.8758. Min Act: -0.0002

Data Index: 76537 (C4 (Web Text))

Max Activating Token Index: 14

Text #15

Max Range: 1.5357. Min Range: -1.5357

Max Act: 1.0184. Min Act: -0.0002

Data Index: 811568 (C4 (Web Text))

Max Activating Token Index: 276

Text #16

Max Range: 1.5357. Min Range: -1.5357

Max Act: 0.9648. Min Act: -0.0003

Data Index: 102105 (C4 (Web Text))

Max Activating Token Index: 367

Text #17

Max Range: 1.5357. Min Range: -1.5357

Max Act: 0.9765. Min Act: -0.0002

Data Index: 286233 (C4 (Web Text))

Max Activating Token Index: 49

Text #18

Max Range: 1.5357. Min Range: -1.5357

Max Act: 1.1019. Min Act: -0.0002

Data Index: 360286 (C4 (Web Text))

Max Activating Token Index: 490

Text #19

Max Range: 1.5357. Min Range: -1.5357

Max Act: 1.0670. Min Act: -0.0002

Data Index: 287616 (C4 (Web Text))

Max Activating Token Index: 991