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

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

Neuron 1108 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: 0.6330. Min Range: -0.6330

Max Act: 0.6330. Min Act: -0.0000

Data Index: 385452 (C4 (Web Text))

Max Activating Token Index: 522

Text #1

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.6277. Min Act: -0.0000

Data Index: 73702 (C4 (Web Text))

Max Activating Token Index: 123

Text #2

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.5076. Min Act: -0.0000

Data Index: 568079 (C4 (Web Text))

Max Activating Token Index: 528

Text #3

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.5400. Min Act: -0.0000

Data Index: 133562 (C4 (Web Text))

Max Activating Token Index: 615

Text #4

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.4151. Min Act: -0.0000

Data Index: 1195492 (C4 (Web Text))

Max Activating Token Index: 510

Text #5

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.3940. Min Act: -0.0000

Data Index: 578375 (C4 (Web Text))

Max Activating Token Index: 203

Text #6

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.3876. Min Act: -0.0000

Data Index: 739142 (C4 (Web Text))

Max Activating Token Index: 825

Text #7

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.4301. Min Act: -0.0000

Data Index: 370858 (C4 (Web Text))

Max Activating Token Index: 700

Text #8

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.3939. Min Act: -0.0000

Data Index: 423293 (C4 (Web Text))

Max Activating Token Index: 307

Text #9

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.3543. Min Act: -0.0000

Data Index: 185226 (C4 (Web Text))

Max Activating Token Index: 819

Text #10

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.3728. Min Act: -0.0000

Data Index: 106080 (C4 (Web Text))

Max Activating Token Index: 344

Text #11

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.3805. Min Act: -0.0000

Data Index: 450104 (C4 (Web Text))

Max Activating Token Index: 517

Text #12

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.3712. Min Act: -0.0000

Data Index: 821005 (C4 (Web Text))

Max Activating Token Index: 924

Text #13

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.3623. Min Act: -0.0000

Data Index: 811379 (C4 (Web Text))

Max Activating Token Index: 923

Text #14

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.3678. Min Act: -0.0000

Data Index: 1234374 (C4 (Web Text))

Max Activating Token Index: 979

Text #15

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.3588. Min Act: -0.0000

Data Index: 106786 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.3366. Min Act: 0.0000

Data Index: 217167 (C4 (Web Text))

Max Activating Token Index: 697

Text #17

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.3156. Min Act: -0.0000

Data Index: 1174170 (C4 (Web Text))

Max Activating Token Index: 756

Text #18

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.3233. Min Act: -0.0000

Data Index: 519742 (C4 (Web Text))

Max Activating Token Index: 1009

Text #19

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.3205. Min Act: 0.0000

Data Index: 1328037 (C4 (Web Text))

Max Activating Token Index: 596