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

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

Neuron 2106 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: 0.2866. Min Range: -0.2866

Max Act: 0.2866. Min Act: -0.0000

Data Index: 461555 (C4 (Web Text))

Max Activating Token Index: 818

Text #1

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2493. Min Act: -0.0000

Data Index: 1269350 (C4 (Web Text))

Max Activating Token Index: 591

Text #2

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2562. Min Act: -0.0000

Data Index: 597462 (C4 (Web Text))

Max Activating Token Index: 881

Text #3

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2683. Min Act: -0.0000

Data Index: 246235 (C4 (Web Text))

Max Activating Token Index: 227

Text #4

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2496. Min Act: -0.0000

Data Index: 912959 (C4 (Web Text))

Max Activating Token Index: 617

Text #5

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2387. Min Act: -0.0000

Data Index: 1325823 (C4 (Web Text))

Max Activating Token Index: 927

Text #6

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2289. Min Act: -0.0000

Data Index: 239900 (C4 (Web Text))

Max Activating Token Index: 76

Text #7

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2231. Min Act: -0.0000

Data Index: 766559 (C4 (Web Text))

Max Activating Token Index: 562

Text #8

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2020. Min Act: -0.0000

Data Index: 198191 (C4 (Web Text))

Max Activating Token Index: 760

Text #9

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2236. Min Act: -0.0000

Data Index: 502664 (C4 (Web Text))

Max Activating Token Index: 177

Text #10

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2337. Min Act: -0.0000

Data Index: 507170 (C4 (Web Text))

Max Activating Token Index: 211

Text #11

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2217. Min Act: -0.0000

Data Index: 934564 (C4 (Web Text))

Max Activating Token Index: 877

Text #12

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2193. Min Act: -0.0000

Data Index: 1024901 (C4 (Web Text))

Max Activating Token Index: 587

Text #13

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2038. Min Act: -0.0000

Data Index: 1072690 (C4 (Web Text))

Max Activating Token Index: 891

Text #14

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2084. Min Act: -0.0000

Data Index: 995845 (C4 (Web Text))

Max Activating Token Index: 533

Text #15

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2091. Min Act: -0.0000

Data Index: 1096572 (C4 (Web Text))

Max Activating Token Index: 83

Text #16

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2137. Min Act: -0.0000

Data Index: 987150 (C4 (Web Text))

Max Activating Token Index: 754

Text #17

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2021. Min Act: -0.0000

Data Index: 598707 (C4 (Web Text))

Max Activating Token Index: 973

Text #18

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2054. Min Act: -0.0000

Data Index: 1082441 (C4 (Web Text))

Max Activating Token Index: 303

Text #19

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.1988. Min Act: -0.0000

Data Index: 603391 (C4 (Web Text))

Max Activating Token Index: 292