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

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

Neuron 4437 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2470. Min Range: -2.2470

Max Act: 2.2470. Min Act: -0.0000

Data Index: 289474 (C4 (Web Text))

Max Activating Token Index: 375

Text #1

Max Range: 2.2470. Min Range: -2.2470

Max Act: 1.9868. Min Act: -0.0000

Data Index: 132449 (C4 (Web Text))

Max Activating Token Index: 792

Text #2

Max Range: 2.2470. Min Range: -2.2470

Max Act: 1.9075. Min Act: -0.0000

Data Index: 967453 (C4 (Web Text))

Max Activating Token Index: 434

Text #3

Max Range: 2.2470. Min Range: -2.2470

Max Act: 1.7338. Min Act: -0.0000

Data Index: 20830 (C4 (Web Text))

Max Activating Token Index: 688

Text #4

Max Range: 2.2470. Min Range: -2.2470

Max Act: 1.7483. Min Act: -0.0000

Data Index: 353309 (C4 (Web Text))

Max Activating Token Index: 871

Text #5

Max Range: 2.2470. Min Range: -2.2470

Max Act: 1.6159. Min Act: -0.0000

Data Index: 1035266 (C4 (Web Text))

Max Activating Token Index: 75

Text #6

Max Range: 2.2470. Min Range: -2.2470

Max Act: 1.5368. Min Act: -0.0000

Data Index: 624322 (C4 (Web Text))

Max Activating Token Index: 230

Text #7

Max Range: 2.2470. Min Range: -2.2470

Max Act: 1.5250. Min Act: -0.0000

Data Index: 811240 (C4 (Web Text))

Max Activating Token Index: 29

Text #8

Max Range: 2.2470. Min Range: -2.2470

Max Act: 1.4842. Min Act: -0.0000

Data Index: 546572 (C4 (Web Text))

Max Activating Token Index: 6

Text #9

Max Range: 2.2470. Min Range: -2.2470

Max Act: 1.4755. Min Act: -0.0000

Data Index: 15981 (C4 (Web Text))

Max Activating Token Index: 457

Text #10

Max Range: 2.2470. Min Range: -2.2470

Max Act: 1.4783. Min Act: -0.0000

Data Index: 1199562 (C4 (Web Text))

Max Activating Token Index: 226

Text #11

Max Range: 2.2470. Min Range: -2.2470

Max Act: 1.4604. Min Act: -0.0000

Data Index: 840022 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 2.2470. Min Range: -2.2470

Max Act: 1.4887. Min Act: -0.0000

Data Index: 983661 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 2.2470. Min Range: -2.2470

Max Act: 1.3310. Min Act: -0.0000

Data Index: 300721 (C4 (Web Text))

Max Activating Token Index: 129

Text #14

Max Range: 2.2470. Min Range: -2.2470

Max Act: 1.3190. Min Act: -0.0000

Data Index: 94726 (C4 (Web Text))

Max Activating Token Index: 835

Text #15

Max Range: 2.2470. Min Range: -2.2470

Max Act: 1.2478. Min Act: -0.0000

Data Index: 417325 (C4 (Web Text))

Max Activating Token Index: 744

Text #16

Max Range: 2.2470. Min Range: -2.2470

Max Act: 1.3293. Min Act: -0.0000

Data Index: 710711 (C4 (Web Text))

Max Activating Token Index: 654

Text #17

Max Range: 2.2470. Min Range: -2.2470

Max Act: 1.2367. Min Act: -0.0000

Data Index: 233613 (C4 (Web Text))

Max Activating Token Index: 128

Text #18

Max Range: 2.2470. Min Range: -2.2470

Max Act: 1.3398. Min Act: -0.0000

Data Index: 294699 (C4 (Web Text))

Max Activating Token Index: 237

Text #19

Max Range: 2.2470. Min Range: -2.2470

Max Act: 1.3030. Min Act: -0.0000

Data Index: 55526 (C4 (Web Text))

Max Activating Token Index: 872