Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2784 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3282. Min Range: -0.3282

Max Act: 0.3104. Min Act: -0.0001

Data Index: 993547 (C4 (Web Text))

Max Activating Token Index: 511

Text #1

Max Range: 0.3282. Min Range: -0.3282

Max Act: 0.3282. Min Act: -0.0001

Data Index: 966495 (C4 (Web Text))

Max Activating Token Index: 106

Text #2

Max Range: 0.3282. Min Range: -0.3282

Max Act: 0.3059. Min Act: -0.0001

Data Index: 1518598 (Python Code)

Max Activating Token Index: 416

Text #3

Max Range: 0.3282. Min Range: -0.3282

Max Act: 0.2957. Min Act: -0.0000

Data Index: 1071131 (C4 (Web Text))

Max Activating Token Index: 951

Text #4

Max Range: 0.3282. Min Range: -0.3282

Max Act: 0.2686. Min Act: -0.0000

Data Index: 457880 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 0.3282. Min Range: -0.3282

Max Act: 0.2702. Min Act: -0.0000

Data Index: 738286 (C4 (Web Text))

Max Activating Token Index: 966

Text #6

Max Range: 0.3282. Min Range: -0.3282

Max Act: 0.2664. Min Act: -0.0000

Data Index: 909273 (C4 (Web Text))

Max Activating Token Index: 353

Text #7

Max Range: 0.3282. Min Range: -0.3282

Max Act: 0.2733. Min Act: -0.0000

Data Index: 798324 (C4 (Web Text))

Max Activating Token Index: 571

Text #8

Max Range: 0.3282. Min Range: -0.3282

Max Act: 0.2376. Min Act: -0.0000

Data Index: 439986 (C4 (Web Text))

Max Activating Token Index: 982

Text #9

Max Range: 0.3282. Min Range: -0.3282

Max Act: 0.2853. Min Act: -0.0000

Data Index: 1063169 (C4 (Web Text))

Max Activating Token Index: 276

Text #10

Max Range: 0.3282. Min Range: -0.3282

Max Act: 0.2541. Min Act: -0.0000

Data Index: 931691 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 0.3282. Min Range: -0.3282

Max Act: 0.2596. Min Act: -0.0001

Data Index: 1420444 (Python Code)

Max Activating Token Index: 664

Text #12

Max Range: 0.3282. Min Range: -0.3282

Max Act: 0.2493. Min Act: -0.0000

Data Index: 504739 (C4 (Web Text))

Max Activating Token Index: 514

Text #13

Max Range: 0.3282. Min Range: -0.3282

Max Act: 0.2791. Min Act: -0.0000

Data Index: 1103973 (C4 (Web Text))

Max Activating Token Index: 649

Text #14

Max Range: 0.3282. Min Range: -0.3282

Max Act: 0.2555. Min Act: -0.0001

Data Index: 387902 (C4 (Web Text))

Max Activating Token Index: 777

Text #15

Max Range: 0.3282. Min Range: -0.3282

Max Act: 0.2358. Min Act: -0.0000

Data Index: 1459344 (Python Code)

Max Activating Token Index: 637

Text #16

Max Range: 0.3282. Min Range: -0.3282

Max Act: 0.2353. Min Act: -0.0001

Data Index: 389160 (C4 (Web Text))

Max Activating Token Index: 891

Text #17

Max Range: 0.3282. Min Range: -0.3282

Max Act: 0.2557. Min Act: -0.0000

Data Index: 272506 (C4 (Web Text))

Max Activating Token Index: 849

Text #18

Max Range: 0.3282. Min Range: -0.3282

Max Act: 0.2476. Min Act: -0.0000

Data Index: 1291240 (C4 (Web Text))

Max Activating Token Index: 645

Text #19

Max Range: 0.3282. Min Range: -0.3282

Max Act: 0.2242. Min Act: -0.0001

Data Index: 1614599 (Python Code)

Max Activating Token Index: 590