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

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

Neuron 614 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.3436. Min Act: -0.0001

Data Index: 525346 (C4 (Web Text))

Max Activating Token Index: 561

Text #1

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.3141. Min Act: -0.0001

Data Index: 481775 (C4 (Web Text))

Max Activating Token Index: 162

Text #2

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2858. Min Act: -0.0002

Data Index: 600093 (C4 (Web Text))

Max Activating Token Index: 58

Text #3

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2976. Min Act: -0.0001

Data Index: 293629 (C4 (Web Text))

Max Activating Token Index: 487

Text #4

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2880. Min Act: -0.0001

Data Index: 1287303 (C4 (Web Text))

Max Activating Token Index: 923

Text #5

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2499. Min Act: -0.0001

Data Index: 1283749 (C4 (Web Text))

Max Activating Token Index: 695

Text #6

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2670. Min Act: -0.0001

Data Index: 1199226 (C4 (Web Text))

Max Activating Token Index: 407

Text #7

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2430. Min Act: -0.0001

Data Index: 764591 (C4 (Web Text))

Max Activating Token Index: 960

Text #8

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2358. Min Act: -0.0001

Data Index: 632233 (C4 (Web Text))

Max Activating Token Index: 395

Text #9

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2621. Min Act: -0.0001

Data Index: 463292 (C4 (Web Text))

Max Activating Token Index: 712

Text #10

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2455. Min Act: -0.0001

Data Index: 621584 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2437. Min Act: -0.0001

Data Index: 54452 (C4 (Web Text))

Max Activating Token Index: 659

Text #12

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2479. Min Act: -0.0001

Data Index: 995187 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2518. Min Act: -0.0002

Data Index: 699928 (C4 (Web Text))

Max Activating Token Index: 555

Text #14

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2478. Min Act: -0.0001

Data Index: 37531 (C4 (Web Text))

Max Activating Token Index: 549

Text #15

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2511. Min Act: -0.0001

Data Index: 1021587 (C4 (Web Text))

Max Activating Token Index: 183

Text #16

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2363. Min Act: -0.0001

Data Index: 384249 (C4 (Web Text))

Max Activating Token Index: 76

Text #17

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2411. Min Act: -0.0001

Data Index: 1013466 (C4 (Web Text))

Max Activating Token Index: 706

Text #18

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2296. Min Act: -0.0001

Data Index: 82776 (C4 (Web Text))

Max Activating Token Index: 483

Text #19

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2374. Min Act: -0.0002

Data Index: 899344 (C4 (Web Text))

Max Activating Token Index: 149