Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2435 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6598. Min Range: -0.6598

Max Act: 0.6598. Min Act: -0.0000

Data Index: 1275343 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 0.6598. Min Range: -0.6598

Max Act: 0.6477. Min Act: -0.0000

Data Index: 1471989 (Python Code)

Max Activating Token Index: 18

Text #2

Max Range: 0.6598. Min Range: -0.6598

Max Act: 0.6281. Min Act: -0.0000

Data Index: 1287952 (C4 (Web Text))

Max Activating Token Index: 948

Text #3

Max Range: 0.6598. Min Range: -0.6598

Max Act: 0.5660. Min Act: -0.0000

Data Index: 829461 (C4 (Web Text))

Max Activating Token Index: 795

Text #4

Max Range: 0.6598. Min Range: -0.6598

Max Act: 0.5922. Min Act: -0.0000

Data Index: 686442 (C4 (Web Text))

Max Activating Token Index: 833

Text #5

Max Range: 0.6598. Min Range: -0.6598

Max Act: 0.6269. Min Act: -0.0000

Data Index: 200294 (C4 (Web Text))

Max Activating Token Index: 850

Text #6

Max Range: 0.6598. Min Range: -0.6598

Max Act: 0.5846. Min Act: -0.0000

Data Index: 325285 (C4 (Web Text))

Max Activating Token Index: 908

Text #7

Max Range: 0.6598. Min Range: -0.6598

Max Act: 0.5737. Min Act: -0.0000

Data Index: 1062145 (C4 (Web Text))

Max Activating Token Index: 986

Text #8

Max Range: 0.6598. Min Range: -0.6598

Max Act: 0.6070. Min Act: -0.0000

Data Index: 326561 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 0.6598. Min Range: -0.6598

Max Act: 0.5426. Min Act: -0.0000

Data Index: 1303295 (C4 (Web Text))

Max Activating Token Index: 302

Text #10

Max Range: 0.6598. Min Range: -0.6598

Max Act: 0.5465. Min Act: -0.0000

Data Index: 1142135 (C4 (Web Text))

Max Activating Token Index: 99

Text #11

Max Range: 0.6598. Min Range: -0.6598

Max Act: 0.5273. Min Act: -0.0000

Data Index: 444493 (C4 (Web Text))

Max Activating Token Index: 749

Text #12

Max Range: 0.6598. Min Range: -0.6598

Max Act: 0.5702. Min Act: -0.0000

Data Index: 438792 (C4 (Web Text))

Max Activating Token Index: 797

Text #13

Max Range: 0.6598. Min Range: -0.6598

Max Act: 0.5521. Min Act: -0.0000

Data Index: 657751 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 0.6598. Min Range: -0.6598

Max Act: 0.5090. Min Act: -0.0000

Data Index: 720458 (C4 (Web Text))

Max Activating Token Index: 480

Text #15

Max Range: 0.6598. Min Range: -0.6598

Max Act: 0.4900. Min Act: -0.0000

Data Index: 584786 (C4 (Web Text))

Max Activating Token Index: 205

Text #16

Max Range: 0.6598. Min Range: -0.6598

Max Act: 0.5444. Min Act: -0.0000

Data Index: 590180 (C4 (Web Text))

Max Activating Token Index: 942

Text #17

Max Range: 0.6598. Min Range: -0.6598

Max Act: 0.5233. Min Act: -0.0000

Data Index: 907830 (C4 (Web Text))

Max Activating Token Index: 686

Text #18

Max Range: 0.6598. Min Range: -0.6598

Max Act: 0.5016. Min Act: -0.0000

Data Index: 748681 (C4 (Web Text))

Max Activating Token Index: 563

Text #19

Max Range: 0.6598. Min Range: -0.6598

Max Act: 0.5329. Min Act: -0.0000

Data Index: 166246 (C4 (Web Text))

Max Activating Token Index: 580