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

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

Neuron 850 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: 0.2493. Min Range: -0.2493

Max Act: 0.2434. Min Act: -0.0000

Data Index: 89659 (C4 (Web Text))

Max Activating Token Index: 785

Text #1

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2402. Min Act: -0.0000

Data Index: 862898 (C4 (Web Text))

Max Activating Token Index: 75

Text #2

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2493. Min Act: -0.0001

Data Index: 250296 (C4 (Web Text))

Max Activating Token Index: 853

Text #3

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2342. Min Act: -0.0000

Data Index: 482584 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2458. Min Act: -0.0000

Data Index: 292854 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2288. Min Act: -0.0000

Data Index: 421494 (C4 (Web Text))

Max Activating Token Index: 1012

Text #6

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2208. Min Act: -0.0000

Data Index: 912609 (C4 (Web Text))

Max Activating Token Index: 1006

Text #7

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2270. Min Act: -0.0000

Data Index: 631172 (C4 (Web Text))

Max Activating Token Index: 189

Text #8

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2211. Min Act: -0.0001

Data Index: 634259 (C4 (Web Text))

Max Activating Token Index: 832

Text #9

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2257. Min Act: -0.0000

Data Index: 640027 (C4 (Web Text))

Max Activating Token Index: 860

Text #10

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2188. Min Act: -0.0001

Data Index: 230087 (C4 (Web Text))

Max Activating Token Index: 881

Text #11

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2133. Min Act: -0.0001

Data Index: 639097 (C4 (Web Text))

Max Activating Token Index: 973

Text #12

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2128. Min Act: -0.0001

Data Index: 286483 (C4 (Web Text))

Max Activating Token Index: 329

Text #13

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2115. Min Act: -0.0000

Data Index: 1103419 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2157. Min Act: -0.0000

Data Index: 1088624 (C4 (Web Text))

Max Activating Token Index: 897

Text #15

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2024. Min Act: -0.0000

Data Index: 124127 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1984. Min Act: -0.0001

Data Index: 738296 (C4 (Web Text))

Max Activating Token Index: 411

Text #17

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1984. Min Act: -0.0000

Data Index: 142975 (C4 (Web Text))

Max Activating Token Index: 275

Text #18

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1977. Min Act: -0.0000

Data Index: 366572 (C4 (Web Text))

Max Activating Token Index: 527

Text #19

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1939. Min Act: -0.0000

Data Index: 1260220 (C4 (Web Text))

Max Activating Token Index: 248