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

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

Neuron 3854 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: 1.0724. Min Range: -1.0724

Max Act: 1.0117. Min Act: -0.0000

Data Index: 452946 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 1.0724. Min Range: -1.0724

Max Act: 1.0157. Min Act: -0.0000

Data Index: 522798 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 1.0724. Min Range: -1.0724

Max Act: 1.0724. Min Act: -0.0000

Data Index: 685462 (C4 (Web Text))

Max Activating Token Index: 202

Text #3

Max Range: 1.0724. Min Range: -1.0724

Max Act: 0.9663. Min Act: -0.0000

Data Index: 729946 (C4 (Web Text))

Max Activating Token Index: 383

Text #4

Max Range: 1.0724. Min Range: -1.0724

Max Act: 0.9571. Min Act: -0.0000

Data Index: 1192812 (C4 (Web Text))

Max Activating Token Index: 885

Text #5

Max Range: 1.0724. Min Range: -1.0724

Max Act: 0.8487. Min Act: -0.0000

Data Index: 751627 (C4 (Web Text))

Max Activating Token Index: 394

Text #6

Max Range: 1.0724. Min Range: -1.0724

Max Act: 0.8723. Min Act: -0.0000

Data Index: 323285 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 1.0724. Min Range: -1.0724

Max Act: 0.8441. Min Act: -0.0000

Data Index: 1341645 (C4 (Web Text))

Max Activating Token Index: 573

Text #8

Max Range: 1.0724. Min Range: -1.0724

Max Act: 0.7984. Min Act: -0.0000

Data Index: 1017829 (C4 (Web Text))

Max Activating Token Index: 705

Text #9

Max Range: 1.0724. Min Range: -1.0724

Max Act: 0.8207. Min Act: -0.0000

Data Index: 106976 (C4 (Web Text))

Max Activating Token Index: 1020

Text #10

Max Range: 1.0724. Min Range: -1.0724

Max Act: 0.7855. Min Act: -0.0000

Data Index: 103348 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 1.0724. Min Range: -1.0724

Max Act: 0.7952. Min Act: -0.0000

Data Index: 279013 (C4 (Web Text))

Max Activating Token Index: 80

Text #12

Max Range: 1.0724. Min Range: -1.0724

Max Act: 0.8085. Min Act: -0.0000

Data Index: 98023 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 1.0724. Min Range: -1.0724

Max Act: 0.8164. Min Act: -0.0000

Data Index: 308049 (C4 (Web Text))

Max Activating Token Index: 328

Text #14

Max Range: 1.0724. Min Range: -1.0724

Max Act: 0.7657. Min Act: -0.0000

Data Index: 631669 (C4 (Web Text))

Max Activating Token Index: 63

Text #15

Max Range: 1.0724. Min Range: -1.0724

Max Act: 0.7679. Min Act: -0.0000

Data Index: 653121 (C4 (Web Text))

Max Activating Token Index: 931

Text #16

Max Range: 1.0724. Min Range: -1.0724

Max Act: 0.7455. Min Act: -0.0000

Data Index: 983807 (C4 (Web Text))

Max Activating Token Index: 620

Text #17

Max Range: 1.0724. Min Range: -1.0724

Max Act: 0.7555. Min Act: -0.0000

Data Index: 1049428 (C4 (Web Text))

Max Activating Token Index: 36

Text #18

Max Range: 1.0724. Min Range: -1.0724

Max Act: 0.7718. Min Act: -0.0000

Data Index: 1334482 (C4 (Web Text))

Max Activating Token Index: 676

Text #19

Max Range: 1.0724. Min Range: -1.0724

Max Act: 0.7245. Min Act: -0.0000

Data Index: 908830 (C4 (Web Text))

Max Activating Token Index: 403