Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1913 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2938. Min Range: -0.2938

Max Act: 0.2938. Min Act: -0.0001

Data Index: 241660 (C4 (Web Text))

Max Activating Token Index: 819

Text #1

Max Range: 0.2938. Min Range: -0.2938

Max Act: 0.2716. Min Act: -0.0000

Data Index: 769368 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 0.2938. Min Range: -0.2938

Max Act: 0.2633. Min Act: -0.0001

Data Index: 104489 (C4 (Web Text))

Max Activating Token Index: 220

Text #3

Max Range: 0.2938. Min Range: -0.2938

Max Act: 0.2296. Min Act: -0.0000

Data Index: 1281496 (C4 (Web Text))

Max Activating Token Index: 726

Text #4

Max Range: 0.2938. Min Range: -0.2938

Max Act: 0.2396. Min Act: -0.0000

Data Index: 458866 (C4 (Web Text))

Max Activating Token Index: 149

Text #5

Max Range: 0.2938. Min Range: -0.2938

Max Act: 0.2384. Min Act: -0.0001

Data Index: 1211725 (C4 (Web Text))

Max Activating Token Index: 338

Text #6

Max Range: 0.2938. Min Range: -0.2938

Max Act: 0.2221. Min Act: -0.0001

Data Index: 1244743 (C4 (Web Text))

Max Activating Token Index: 257

Text #7

Max Range: 0.2938. Min Range: -0.2938

Max Act: 0.2265. Min Act: -0.0000

Data Index: 520566 (C4 (Web Text))

Max Activating Token Index: 814

Text #8

Max Range: 0.2938. Min Range: -0.2938

Max Act: 0.2166. Min Act: -0.0001

Data Index: 668435 (C4 (Web Text))

Max Activating Token Index: 766

Text #9

Max Range: 0.2938. Min Range: -0.2938

Max Act: 0.2131. Min Act: -0.0001

Data Index: 1052927 (C4 (Web Text))

Max Activating Token Index: 372

Text #10

Max Range: 0.2938. Min Range: -0.2938

Max Act: 0.2071. Min Act: -0.0001

Data Index: 603091 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 0.2938. Min Range: -0.2938

Max Act: 0.2046. Min Act: -0.0000

Data Index: 170266 (C4 (Web Text))

Max Activating Token Index: 1011

Text #12

Max Range: 0.2938. Min Range: -0.2938

Max Act: 0.2087. Min Act: -0.0001

Data Index: 1152896 (C4 (Web Text))

Max Activating Token Index: 751

Text #13

Max Range: 0.2938. Min Range: -0.2938

Max Act: 0.1953. Min Act: -0.0001

Data Index: 773208 (C4 (Web Text))

Max Activating Token Index: 883

Text #14

Max Range: 0.2938. Min Range: -0.2938

Max Act: 0.1998. Min Act: -0.0000

Data Index: 224585 (C4 (Web Text))

Max Activating Token Index: 432

Text #15

Max Range: 0.2938. Min Range: -0.2938

Max Act: 0.2188. Min Act: -0.0001

Data Index: 903496 (C4 (Web Text))

Max Activating Token Index: 646

Text #16

Max Range: 0.2938. Min Range: -0.2938

Max Act: 0.2047. Min Act: -0.0000

Data Index: 1202227 (C4 (Web Text))

Max Activating Token Index: 143

Text #17

Max Range: 0.2938. Min Range: -0.2938

Max Act: 0.1922. Min Act: -0.0001

Data Index: 744642 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 0.2938. Min Range: -0.2938

Max Act: 0.1923. Min Act: -0.0000

Data Index: 262797 (C4 (Web Text))

Max Activating Token Index: 333

Text #19

Max Range: 0.2938. Min Range: -0.2938

Max Act: 0.1910. Min Act: -0.0000

Data Index: 64502 (C4 (Web Text))

Max Activating Token Index: 917