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

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

Neuron 1066 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2406. Min Range: -2.2406

Max Act: 2.2406. Min Act: -0.0000

Data Index: 733367 (C4 (Web Text))

Max Activating Token Index: 569

Text #1

Max Range: 2.2406. Min Range: -2.2406

Max Act: 2.1044. Min Act: -0.0000

Data Index: 522537 (C4 (Web Text))

Max Activating Token Index: 658

Text #2

Max Range: 2.2406. Min Range: -2.2406

Max Act: 1.9383. Min Act: -0.0000

Data Index: 48347 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 2.2406. Min Range: -2.2406

Max Act: 1.8895. Min Act: -0.0000

Data Index: 1285999 (C4 (Web Text))

Max Activating Token Index: 827

Text #4

Max Range: 2.2406. Min Range: -2.2406

Max Act: 1.8414. Min Act: -0.0000

Data Index: 859254 (C4 (Web Text))

Max Activating Token Index: 417

Text #5

Max Range: 2.2406. Min Range: -2.2406

Max Act: 1.8301. Min Act: -0.0000

Data Index: 460343 (C4 (Web Text))

Max Activating Token Index: 487

Text #6

Max Range: 2.2406. Min Range: -2.2406

Max Act: 1.7222. Min Act: -0.0000

Data Index: 903525 (C4 (Web Text))

Max Activating Token Index: 597

Text #7

Max Range: 2.2406. Min Range: -2.2406

Max Act: 1.6814. Min Act: -0.0000

Data Index: 89510 (C4 (Web Text))

Max Activating Token Index: 513

Text #8

Max Range: 2.2406. Min Range: -2.2406

Max Act: 1.6734. Min Act: -0.0000

Data Index: 1146712 (C4 (Web Text))

Max Activating Token Index: 730

Text #9

Max Range: 2.2406. Min Range: -2.2406

Max Act: 1.6539. Min Act: -0.0000

Data Index: 1182538 (C4 (Web Text))

Max Activating Token Index: 62

Text #10

Max Range: 2.2406. Min Range: -2.2406

Max Act: 1.6500. Min Act: -0.0000

Data Index: 682108 (C4 (Web Text))

Max Activating Token Index: 336

Text #11

Max Range: 2.2406. Min Range: -2.2406

Max Act: 1.6317. Min Act: -0.0000

Data Index: 750290 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 2.2406. Min Range: -2.2406

Max Act: 1.5381. Min Act: -0.0000

Data Index: 99575 (C4 (Web Text))

Max Activating Token Index: 806

Text #13

Max Range: 2.2406. Min Range: -2.2406

Max Act: 1.5936. Min Act: -0.0000

Data Index: 307069 (C4 (Web Text))

Max Activating Token Index: 927

Text #14

Max Range: 2.2406. Min Range: -2.2406

Max Act: 1.5765. Min Act: -0.0000

Data Index: 983165 (C4 (Web Text))

Max Activating Token Index: 997

Text #15

Max Range: 2.2406. Min Range: -2.2406

Max Act: 1.4715. Min Act: -0.0000

Data Index: 819079 (C4 (Web Text))

Max Activating Token Index: 962

Text #16

Max Range: 2.2406. Min Range: -2.2406

Max Act: 1.6607. Min Act: -0.0000

Data Index: 796388 (C4 (Web Text))

Max Activating Token Index: 733

Text #17

Max Range: 2.2406. Min Range: -2.2406

Max Act: 1.5660. Min Act: -0.0000

Data Index: 147468 (C4 (Web Text))

Max Activating Token Index: 498

Text #18

Max Range: 2.2406. Min Range: -2.2406

Max Act: 1.5653. Min Act: -0.0000

Data Index: 1233296 (C4 (Web Text))

Max Activating Token Index: 231

Text #19

Max Range: 2.2406. Min Range: -2.2406

Max Act: 1.3453. Min Act: -0.0000

Data Index: 943010 (C4 (Web Text))

Max Activating Token Index: 209