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

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

Neuron 4494 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.4868. Min Act: -0.0001

Data Index: 1042455 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.2890. Min Act: -0.0000

Data Index: 429064 (C4 (Web Text))

Max Activating Token Index: 373

Text #2

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.5373. Min Act: -0.0000

Data Index: 1297980 (C4 (Web Text))

Max Activating Token Index: 595

Text #3

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.4829. Min Act: -0.0000

Data Index: 611354 (C4 (Web Text))

Max Activating Token Index: 352

Text #4

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.4861. Min Act: -0.0000

Data Index: 842307 (C4 (Web Text))

Max Activating Token Index: 818

Text #5

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.4577. Min Act: -0.0000

Data Index: 1253551 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.4770. Min Act: -0.0000

Data Index: 109876 (C4 (Web Text))

Max Activating Token Index: 612

Text #7

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.3628. Min Act: -0.0000

Data Index: 755980 (C4 (Web Text))

Max Activating Token Index: 733

Text #8

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.4211. Min Act: -0.0000

Data Index: 31547 (C4 (Web Text))

Max Activating Token Index: 809

Text #9

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.3328. Min Act: -0.0000

Data Index: 581223 (C4 (Web Text))

Max Activating Token Index: 557

Text #10

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.3085. Min Act: -0.0000

Data Index: 508460 (C4 (Web Text))

Max Activating Token Index: 270

Text #11

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.2860. Min Act: -0.0000

Data Index: 207409 (C4 (Web Text))

Max Activating Token Index: 205

Text #12

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.3674. Min Act: -0.0000

Data Index: 494462 (C4 (Web Text))

Max Activating Token Index: 396

Text #13

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.3172. Min Act: -0.0000

Data Index: 1107656 (C4 (Web Text))

Max Activating Token Index: 927

Text #14

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.2431. Min Act: -0.0000

Data Index: 394126 (C4 (Web Text))

Max Activating Token Index: 6

Text #15

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.2803. Min Act: -0.0000

Data Index: 589429 (C4 (Web Text))

Max Activating Token Index: 87

Text #16

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.3020. Min Act: -0.0000

Data Index: 90692 (C4 (Web Text))

Max Activating Token Index: 336

Text #17

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.3532. Min Act: -0.0000

Data Index: 539964 (C4 (Web Text))

Max Activating Token Index: 414

Text #18

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.2654. Min Act: -0.0000

Data Index: 1239031 (C4 (Web Text))

Max Activating Token Index: 772

Text #19

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.2527. Min Act: -0.0000

Data Index: 412556 (C4 (Web Text))

Max Activating Token Index: 455