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

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

Neuron 314 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2410. Min Range: -0.2410

Max Act: 0.2410. Min Act: -0.0000

Data Index: 256133 (C4 (Web Text))

Max Activating Token Index: 219

Text #1

Max Range: 0.2410. Min Range: -0.2410

Max Act: 0.2277. Min Act: -0.0000

Data Index: 168957 (C4 (Web Text))

Max Activating Token Index: 1014

Text #2

Max Range: 0.2410. Min Range: -0.2410

Max Act: 0.2193. Min Act: -0.0000

Data Index: 701414 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 0.2410. Min Range: -0.2410

Max Act: 0.2237. Min Act: -0.0000

Data Index: 485830 (C4 (Web Text))

Max Activating Token Index: 674

Text #4

Max Range: 0.2410. Min Range: -0.2410

Max Act: 0.2105. Min Act: -0.0000

Data Index: 975559 (C4 (Web Text))

Max Activating Token Index: 423

Text #5

Max Range: 0.2410. Min Range: -0.2410

Max Act: 0.1959. Min Act: -0.0000

Data Index: 929343 (C4 (Web Text))

Max Activating Token Index: 390

Text #6

Max Range: 0.2410. Min Range: -0.2410

Max Act: 0.2110. Min Act: -0.0000

Data Index: 508644 (C4 (Web Text))

Max Activating Token Index: 961

Text #7

Max Range: 0.2410. Min Range: -0.2410

Max Act: 0.1958. Min Act: -0.0000

Data Index: 988768 (C4 (Web Text))

Max Activating Token Index: 231

Text #8

Max Range: 0.2410. Min Range: -0.2410

Max Act: 0.2064. Min Act: -0.0000

Data Index: 900583 (C4 (Web Text))

Max Activating Token Index: 364

Text #9

Max Range: 0.2410. Min Range: -0.2410

Max Act: 0.2055. Min Act: -0.0000

Data Index: 433397 (C4 (Web Text))

Max Activating Token Index: 134

Text #10

Max Range: 0.2410. Min Range: -0.2410

Max Act: 0.2045. Min Act: -0.0000

Data Index: 636701 (C4 (Web Text))

Max Activating Token Index: 627

Text #11

Max Range: 0.2410. Min Range: -0.2410

Max Act: 0.1974. Min Act: -0.0000

Data Index: 468267 (C4 (Web Text))

Max Activating Token Index: 23

Text #12

Max Range: 0.2410. Min Range: -0.2410

Max Act: 0.1966. Min Act: -0.0000

Data Index: 820075 (C4 (Web Text))

Max Activating Token Index: 416

Text #13

Max Range: 0.2410. Min Range: -0.2410

Max Act: 0.1971. Min Act: -0.0000

Data Index: 441686 (C4 (Web Text))

Max Activating Token Index: 230

Text #14

Max Range: 0.2410. Min Range: -0.2410

Max Act: 0.1965. Min Act: -0.0000

Data Index: 516499 (C4 (Web Text))

Max Activating Token Index: 660

Text #15

Max Range: 0.2410. Min Range: -0.2410

Max Act: 0.1934. Min Act: -0.0000

Data Index: 569422 (C4 (Web Text))

Max Activating Token Index: 99

Text #16

Max Range: 0.2410. Min Range: -0.2410

Max Act: 0.1841. Min Act: -0.0000

Data Index: 995198 (C4 (Web Text))

Max Activating Token Index: 938

Text #17

Max Range: 0.2410. Min Range: -0.2410

Max Act: 0.1964. Min Act: -0.0000

Data Index: 308467 (C4 (Web Text))

Max Activating Token Index: 162

Text #18

Max Range: 0.2410. Min Range: -0.2410

Max Act: 0.1896. Min Act: -0.0000

Data Index: 808407 (C4 (Web Text))

Max Activating Token Index: 798

Text #19

Max Range: 0.2410. Min Range: -0.2410

Max Act: 0.1820. Min Act: -0.0000

Data Index: 964896 (C4 (Web Text))

Max Activating Token Index: 89