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

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

Neuron 4384 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.9297. Min Act: -0.0000

Data Index: 560825 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.7544. Min Act: -0.0000

Data Index: 401525 (C4 (Web Text))

Max Activating Token Index: 312

Text #2

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.6937. Min Act: -0.0000

Data Index: 876590 (C4 (Web Text))

Max Activating Token Index: 458

Text #3

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.6024. Min Act: -0.0000

Data Index: 1003433 (C4 (Web Text))

Max Activating Token Index: 541

Text #4

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.6337. Min Act: -0.0000

Data Index: 900147 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.5472. Min Act: -0.0000

Data Index: 921609 (C4 (Web Text))

Max Activating Token Index: 131

Text #6

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.5268. Min Act: -0.0000

Data Index: 479411 (C4 (Web Text))

Max Activating Token Index: 921

Text #7

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.5286. Min Act: -0.0000

Data Index: 85433 (C4 (Web Text))

Max Activating Token Index: 986

Text #8

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.5277. Min Act: -0.0000

Data Index: 775532 (C4 (Web Text))

Max Activating Token Index: 255

Text #9

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.4889. Min Act: -0.0000

Data Index: 398371 (C4 (Web Text))

Max Activating Token Index: 479

Text #10

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.4526. Min Act: -0.0000

Data Index: 662790 (C4 (Web Text))

Max Activating Token Index: 359

Text #11

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.4069. Min Act: -0.0000

Data Index: 719978 (C4 (Web Text))

Max Activating Token Index: 872

Text #12

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.4252. Min Act: -0.0000

Data Index: 517764 (C4 (Web Text))

Max Activating Token Index: 542

Text #13

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.3615. Min Act: -0.0000

Data Index: 175886 (C4 (Web Text))

Max Activating Token Index: 833

Text #14

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.3905. Min Act: -0.0000

Data Index: 1116075 (C4 (Web Text))

Max Activating Token Index: 36

Text #15

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.3683. Min Act: -0.0000

Data Index: 1239589 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.3870. Min Act: -0.0000

Data Index: 564978 (C4 (Web Text))

Max Activating Token Index: 570

Text #17

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.3579. Min Act: -0.0000

Data Index: 219548 (C4 (Web Text))

Max Activating Token Index: 953

Text #18

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.3727. Min Act: -0.0000

Data Index: 864319 (C4 (Web Text))

Max Activating Token Index: 253

Text #19

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.3441. Min Act: -0.0000

Data Index: 105274 (C4 (Web Text))

Max Activating Token Index: 810