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

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

Neuron 3470 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: 5.7562. Min Range: -5.7562

Max Act: 5.6558. Min Act: -0.0000

Data Index: 407238 (C4 (Web Text))

Max Activating Token Index: 877

Text #1

Max Range: 5.7562. Min Range: -5.7562

Max Act: 5.6657. Min Act: -0.0000

Data Index: 1077539 (C4 (Web Text))

Max Activating Token Index: 419

Text #2

Max Range: 5.7562. Min Range: -5.7562

Max Act: 5.7562. Min Act: -0.0000

Data Index: 669889 (C4 (Web Text))

Max Activating Token Index: 752

Text #3

Max Range: 5.7562. Min Range: -5.7562

Max Act: 5.2514. Min Act: -0.0000

Data Index: 325940 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 5.7562. Min Range: -5.7562

Max Act: 5.4193. Min Act: -0.0000

Data Index: 1200763 (C4 (Web Text))

Max Activating Token Index: 765

Text #5

Max Range: 5.7562. Min Range: -5.7562

Max Act: 5.3523. Min Act: -0.0000

Data Index: 1312889 (C4 (Web Text))

Max Activating Token Index: 860

Text #6

Max Range: 5.7562. Min Range: -5.7562

Max Act: 5.3179. Min Act: -0.0000

Data Index: 1111170 (C4 (Web Text))

Max Activating Token Index: 896

Text #7

Max Range: 5.7562. Min Range: -5.7562

Max Act: 5.1103. Min Act: -0.0000

Data Index: 239968 (C4 (Web Text))

Max Activating Token Index: 535

Text #8

Max Range: 5.7562. Min Range: -5.7562

Max Act: 5.2632. Min Act: -0.0000

Data Index: 631188 (C4 (Web Text))

Max Activating Token Index: 704

Text #9

Max Range: 5.7562. Min Range: -5.7562

Max Act: 5.2405. Min Act: -0.0000

Data Index: 644502 (C4 (Web Text))

Max Activating Token Index: 66

Text #10

Max Range: 5.7562. Min Range: -5.7562

Max Act: 5.4096. Min Act: -0.0000

Data Index: 87294 (C4 (Web Text))

Max Activating Token Index: 981

Text #11

Max Range: 5.7562. Min Range: -5.7562

Max Act: 5.2206. Min Act: -0.0000

Data Index: 148772 (C4 (Web Text))

Max Activating Token Index: 76

Text #12

Max Range: 5.7562. Min Range: -5.7562

Max Act: 4.8622. Min Act: -0.0000

Data Index: 38043 (C4 (Web Text))

Max Activating Token Index: 317

Text #13

Max Range: 5.7562. Min Range: -5.7562

Max Act: 5.2024. Min Act: -0.0000

Data Index: 1333049 (C4 (Web Text))

Max Activating Token Index: 54

Text #14

Max Range: 5.7562. Min Range: -5.7562

Max Act: 4.8546. Min Act: -0.0000

Data Index: 365864 (C4 (Web Text))

Max Activating Token Index: 327

Text #15

Max Range: 5.7562. Min Range: -5.7562

Max Act: 5.3660. Min Act: -0.0000

Data Index: 1123946 (C4 (Web Text))

Max Activating Token Index: 182

Text #16

Max Range: 5.7562. Min Range: -5.7562

Max Act: 4.9935. Min Act: -0.0000

Data Index: 382435 (C4 (Web Text))

Max Activating Token Index: 472

Text #17

Max Range: 5.7562. Min Range: -5.7562

Max Act: 5.1837. Min Act: -0.0000

Data Index: 1333552 (C4 (Web Text))

Max Activating Token Index: 393

Text #18

Max Range: 5.7562. Min Range: -5.7562

Max Act: 5.3359. Min Act: -0.0000

Data Index: 1101141 (C4 (Web Text))

Max Activating Token Index: 317

Text #19

Max Range: 5.7562. Min Range: -5.7562

Max Act: 5.1526. Min Act: -0.0000

Data Index: 681070 (C4 (Web Text))

Max Activating Token Index: 17