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

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

Neuron 1902 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0402. Min Act: -0.0002

Data Index: 873799 (C4 (Web Text))

Max Activating Token Index: 808

Text #1

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0360. Min Act: -0.0002

Data Index: 220489 (C4 (Web Text))

Max Activating Token Index: 813

Text #2

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0350. Min Act: -0.0002

Data Index: 505521 (C4 (Web Text))

Max Activating Token Index: 221

Text #3

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0355. Min Act: -0.0002

Data Index: 496910 (C4 (Web Text))

Max Activating Token Index: 542

Text #4

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0339. Min Act: -0.0002

Data Index: 336904 (C4 (Web Text))

Max Activating Token Index: 70

Text #5

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0344. Min Act: -0.0002

Data Index: 1234721 (C4 (Web Text))

Max Activating Token Index: 709

Text #6

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0324. Min Act: -0.0002

Data Index: 659818 (C4 (Web Text))

Max Activating Token Index: 944

Text #7

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0335. Min Act: -0.0002

Data Index: 1349694 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0324. Min Act: -0.0002

Data Index: 18060 (C4 (Web Text))

Max Activating Token Index: 710

Text #9

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0322. Min Act: -0.0002

Data Index: 1052743 (C4 (Web Text))

Max Activating Token Index: 734

Text #10

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0321. Min Act: -0.0002

Data Index: 395424 (C4 (Web Text))

Max Activating Token Index: 737

Text #11

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0317. Min Act: -0.0002

Data Index: 654242 (C4 (Web Text))

Max Activating Token Index: 124

Text #12

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0314. Min Act: -0.0002

Data Index: 298441 (C4 (Web Text))

Max Activating Token Index: 985

Text #13

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0312. Min Act: -0.0002

Data Index: 174846 (C4 (Web Text))

Max Activating Token Index: 827

Text #14

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0310. Min Act: -0.0002

Data Index: 13569 (C4 (Web Text))

Max Activating Token Index: 683

Text #15

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0312. Min Act: -0.0002

Data Index: 708107 (C4 (Web Text))

Max Activating Token Index: 105

Text #16

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0304. Min Act: -0.0002

Data Index: 1264116 (C4 (Web Text))

Max Activating Token Index: 314

Text #17

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0308. Min Act: -0.0002

Data Index: 684566 (C4 (Web Text))

Max Activating Token Index: 608

Text #18

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0296. Min Act: -0.0002

Data Index: 553370 (C4 (Web Text))

Max Activating Token Index: 254

Text #19

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0292. Min Act: -0.0002

Data Index: 256935 (C4 (Web Text))

Max Activating Token Index: 937