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

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

Neuron 4179 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8041. Min Range: -2.8041

Max Act: 2.8041. Min Act: -0.0000

Data Index: 296045 (C4 (Web Text))

Max Activating Token Index: 429

Text #1

Max Range: 2.8041. Min Range: -2.8041

Max Act: 2.0990. Min Act: -0.0000

Data Index: 693792 (C4 (Web Text))

Max Activating Token Index: 599

Text #2

Max Range: 2.8041. Min Range: -2.8041

Max Act: 1.9462. Min Act: -0.0000

Data Index: 666692 (C4 (Web Text))

Max Activating Token Index: 255

Text #3

Max Range: 2.8041. Min Range: -2.8041

Max Act: 1.6274. Min Act: -0.0000

Data Index: 171251 (C4 (Web Text))

Max Activating Token Index: 590

Text #4

Max Range: 2.8041. Min Range: -2.8041

Max Act: 1.3810. Min Act: -0.0000

Data Index: 862636 (C4 (Web Text))

Max Activating Token Index: 535

Text #5

Max Range: 2.8041. Min Range: -2.8041

Max Act: 1.4479. Min Act: -0.0000

Data Index: 507972 (C4 (Web Text))

Max Activating Token Index: 414

Text #6

Max Range: 2.8041. Min Range: -2.8041

Max Act: 1.3359. Min Act: -0.0000

Data Index: 429291 (C4 (Web Text))

Max Activating Token Index: 680

Text #7

Max Range: 2.8041. Min Range: -2.8041

Max Act: 1.3228. Min Act: -0.0000

Data Index: 311600 (C4 (Web Text))

Max Activating Token Index: 859

Text #8

Max Range: 2.8041. Min Range: -2.8041

Max Act: 1.3875. Min Act: -0.0000

Data Index: 1314819 (C4 (Web Text))

Max Activating Token Index: 338

Text #9

Max Range: 2.8041. Min Range: -2.8041

Max Act: 1.3321. Min Act: -0.0000

Data Index: 46582 (C4 (Web Text))

Max Activating Token Index: 894

Text #10

Max Range: 2.8041. Min Range: -2.8041

Max Act: 1.3038. Min Act: -0.0000

Data Index: 867528 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 2.8041. Min Range: -2.8041

Max Act: 1.1867. Min Act: -0.0000

Data Index: 864118 (C4 (Web Text))

Max Activating Token Index: 713

Text #12

Max Range: 2.8041. Min Range: -2.8041

Max Act: 1.2382. Min Act: -0.0000

Data Index: 1357813 (C4 (Web Text))

Max Activating Token Index: 569

Text #13

Max Range: 2.8041. Min Range: -2.8041

Max Act: 1.2257. Min Act: -0.0000

Data Index: 459426 (C4 (Web Text))

Max Activating Token Index: 1002

Text #14

Max Range: 2.8041. Min Range: -2.8041

Max Act: 1.2219. Min Act: -0.0000

Data Index: 1338294 (C4 (Web Text))

Max Activating Token Index: 423

Text #15

Max Range: 2.8041. Min Range: -2.8041

Max Act: 1.2009. Min Act: -0.0000

Data Index: 673841 (C4 (Web Text))

Max Activating Token Index: 1013

Text #16

Max Range: 2.8041. Min Range: -2.8041

Max Act: 1.1939. Min Act: -0.0000

Data Index: 601584 (C4 (Web Text))

Max Activating Token Index: 414

Text #17

Max Range: 2.8041. Min Range: -2.8041

Max Act: 1.2592. Min Act: -0.0000

Data Index: 941304 (C4 (Web Text))

Max Activating Token Index: 917

Text #18

Max Range: 2.8041. Min Range: -2.8041

Max Act: 1.1957. Min Act: -0.0000

Data Index: 757114 (C4 (Web Text))

Max Activating Token Index: 137

Text #19

Max Range: 2.8041. Min Range: -2.8041

Max Act: 1.1175. Min Act: -0.0000

Data Index: 348602 (C4 (Web Text))

Max Activating Token Index: 503