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

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

Neuron 1825 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.2308. Min Act: -0.0000

Data Index: 711497 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.2218. Min Act: -0.0001

Data Index: 914235 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.2160. Min Act: -0.0000

Data Index: 287938 (C4 (Web Text))

Max Activating Token Index: 729

Text #3

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.2232. Min Act: -0.0000

Data Index: 1057694 (C4 (Web Text))

Max Activating Token Index: 979

Text #4

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.2115. Min Act: -0.0000

Data Index: 910114 (C4 (Web Text))

Max Activating Token Index: 856

Text #5

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.2237. Min Act: -0.0000

Data Index: 718739 (C4 (Web Text))

Max Activating Token Index: 193

Text #6

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.2155. Min Act: -0.0001

Data Index: 1304767 (C4 (Web Text))

Max Activating Token Index: 443

Text #7

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1862. Min Act: -0.0000

Data Index: 1014074 (C4 (Web Text))

Max Activating Token Index: 756

Text #8

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1970. Min Act: -0.0000

Data Index: 55732 (C4 (Web Text))

Max Activating Token Index: 111

Text #9

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.2126. Min Act: -0.0000

Data Index: 867587 (C4 (Web Text))

Max Activating Token Index: 663

Text #10

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.2039. Min Act: -0.0000

Data Index: 466343 (C4 (Web Text))

Max Activating Token Index: 881

Text #11

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1927. Min Act: -0.0000

Data Index: 806650 (C4 (Web Text))

Max Activating Token Index: 912

Text #12

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.2067. Min Act: -0.0001

Data Index: 765950 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1970. Min Act: -0.0000

Data Index: 673043 (C4 (Web Text))

Max Activating Token Index: 348

Text #14

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1953. Min Act: -0.0000

Data Index: 1013625 (C4 (Web Text))

Max Activating Token Index: 603

Text #15

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1954. Min Act: -0.0000

Data Index: 1172942 (C4 (Web Text))

Max Activating Token Index: 112

Text #16

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1983. Min Act: -0.0000

Data Index: 1041716 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1900. Min Act: -0.0000

Data Index: 277957 (C4 (Web Text))

Max Activating Token Index: 65

Text #18

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1707. Min Act: -0.0000

Data Index: 70433 (C4 (Web Text))

Max Activating Token Index: 344

Text #19

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.2135. Min Act: -0.0000

Data Index: 234735 (C4 (Web Text))

Max Activating Token Index: 825