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

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

Neuron 361 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9278. Min Range: -1.9278

Max Act: 1.9278. Min Act: -0.0000

Data Index: 1354772 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 1.9278. Min Range: -1.9278

Max Act: 1.8275. Min Act: -0.0000

Data Index: 655261 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 1.9278. Min Range: -1.9278

Max Act: 1.7283. Min Act: -0.0000

Data Index: 1459251 (Python Code)

Max Activating Token Index: 865

Text #3

Max Range: 1.9278. Min Range: -1.9278

Max Act: 1.8645. Min Act: 0.0001

Data Index: 1425126 (Python Code)

Max Activating Token Index: 292

Text #4

Max Range: 1.9278. Min Range: -1.9278

Max Act: 1.8190. Min Act: 0.0000

Data Index: 1028482 (C4 (Web Text))

Max Activating Token Index: 698

Text #5

Max Range: 1.9278. Min Range: -1.9278

Max Act: 1.6754. Min Act: -0.0000

Data Index: 826924 (C4 (Web Text))

Max Activating Token Index: 649

Text #6

Max Range: 1.9278. Min Range: -1.9278

Max Act: 1.6281. Min Act: -0.0000

Data Index: 96904 (C4 (Web Text))

Max Activating Token Index: 596

Text #7

Max Range: 1.9278. Min Range: -1.9278

Max Act: 1.6845. Min Act: -0.0000

Data Index: 1546643 (Python Code)

Max Activating Token Index: 674

Text #8

Max Range: 1.9278. Min Range: -1.9278

Max Act: 1.6322. Min Act: -0.0000

Data Index: 1447347 (Python Code)

Max Activating Token Index: 773

Text #9

Max Range: 1.9278. Min Range: -1.9278

Max Act: 1.5776. Min Act: -0.0000

Data Index: 1224730 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 1.9278. Min Range: -1.9278

Max Act: 1.6088. Min Act: -0.0000

Data Index: 1599008 (Python Code)

Max Activating Token Index: 584

Text #11

Max Range: 1.9278. Min Range: -1.9278

Max Act: 1.5082. Min Act: -0.0000

Data Index: 811369 (C4 (Web Text))

Max Activating Token Index: 328

Text #12

Max Range: 1.9278. Min Range: -1.9278

Max Act: 1.5985. Min Act: -0.0000

Data Index: 624453 (C4 (Web Text))

Max Activating Token Index: 983

Text #13

Max Range: 1.9278. Min Range: -1.9278

Max Act: 1.4854. Min Act: -0.0000

Data Index: 287233 (C4 (Web Text))

Max Activating Token Index: 522

Text #14

Max Range: 1.9278. Min Range: -1.9278

Max Act: 1.4822. Min Act: -0.0000

Data Index: 1144731 (C4 (Web Text))

Max Activating Token Index: 985

Text #15

Max Range: 1.9278. Min Range: -1.9278

Max Act: 1.5552. Min Act: -0.0000

Data Index: 1383130 (Python Code)

Max Activating Token Index: 604

Text #16

Max Range: 1.9278. Min Range: -1.9278

Max Act: 1.4470. Min Act: 0.0001

Data Index: 1396299 (Python Code)

Max Activating Token Index: 234

Text #17

Max Range: 1.9278. Min Range: -1.9278

Max Act: 1.3627. Min Act: -0.0000

Data Index: 822193 (C4 (Web Text))

Max Activating Token Index: 534

Text #18

Max Range: 1.9278. Min Range: -1.9278

Max Act: 1.3525. Min Act: -0.0000

Data Index: 1301288 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 1.9278. Min Range: -1.9278

Max Act: 1.4184. Min Act: -0.0000

Data Index: 1585883 (Python Code)

Max Activating Token Index: 113