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

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

Neuron 1049 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: 0.2868. Min Range: -0.2868

Max Act: 0.2868. Min Act: -0.0001

Data Index: 328257 (C4 (Web Text))

Max Activating Token Index: 743

Text #1

Max Range: 0.2868. Min Range: -0.2868

Max Act: 0.2653. Min Act: -0.0000

Data Index: 1176477 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 0.2868. Min Range: -0.2868

Max Act: 0.2430. Min Act: -0.0001

Data Index: 207464 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 0.2868. Min Range: -0.2868

Max Act: 0.2321. Min Act: -0.0001

Data Index: 1095879 (C4 (Web Text))

Max Activating Token Index: 549

Text #4

Max Range: 0.2868. Min Range: -0.2868

Max Act: 0.2385. Min Act: -0.0000

Data Index: 220486 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 0.2868. Min Range: -0.2868

Max Act: 0.2274. Min Act: -0.0000

Data Index: 623498 (C4 (Web Text))

Max Activating Token Index: 885

Text #6

Max Range: 0.2868. Min Range: -0.2868

Max Act: 0.2229. Min Act: -0.0001

Data Index: 292908 (C4 (Web Text))

Max Activating Token Index: 667

Text #7

Max Range: 0.2868. Min Range: -0.2868

Max Act: 0.2307. Min Act: -0.0001

Data Index: 582053 (C4 (Web Text))

Max Activating Token Index: 783

Text #8

Max Range: 0.2868. Min Range: -0.2868

Max Act: 0.2292. Min Act: -0.0000

Data Index: 367871 (C4 (Web Text))

Max Activating Token Index: 642

Text #9

Max Range: 0.2868. Min Range: -0.2868

Max Act: 0.2253. Min Act: -0.0000

Data Index: 348109 (C4 (Web Text))

Max Activating Token Index: 279

Text #10

Max Range: 0.2868. Min Range: -0.2868

Max Act: 0.2225. Min Act: -0.0001

Data Index: 1076298 (C4 (Web Text))

Max Activating Token Index: 120

Text #11

Max Range: 0.2868. Min Range: -0.2868

Max Act: 0.2149. Min Act: -0.0001

Data Index: 319159 (C4 (Web Text))

Max Activating Token Index: 149

Text #12

Max Range: 0.2868. Min Range: -0.2868

Max Act: 0.2105. Min Act: -0.0001

Data Index: 868412 (C4 (Web Text))

Max Activating Token Index: 617

Text #13

Max Range: 0.2868. Min Range: -0.2868

Max Act: 0.2008. Min Act: -0.0001

Data Index: 1358017 (C4 (Web Text))

Max Activating Token Index: 245

Text #14

Max Range: 0.2868. Min Range: -0.2868

Max Act: 0.2081. Min Act: -0.0001

Data Index: 648074 (C4 (Web Text))

Max Activating Token Index: 136

Text #15

Max Range: 0.2868. Min Range: -0.2868

Max Act: 0.1984. Min Act: -0.0000

Data Index: 1289365 (C4 (Web Text))

Max Activating Token Index: 571

Text #16

Max Range: 0.2868. Min Range: -0.2868

Max Act: 0.2047. Min Act: -0.0001

Data Index: 907543 (C4 (Web Text))

Max Activating Token Index: 642

Text #17

Max Range: 0.2868. Min Range: -0.2868

Max Act: 0.2039. Min Act: -0.0000

Data Index: 1259738 (C4 (Web Text))

Max Activating Token Index: 992

Text #18

Max Range: 0.2868. Min Range: -0.2868

Max Act: 0.1961. Min Act: -0.0000

Data Index: 51648 (C4 (Web Text))

Max Activating Token Index: 56

Text #19

Max Range: 0.2868. Min Range: -0.2868

Max Act: 0.2185. Min Act: -0.0000

Data Index: 852323 (C4 (Web Text))

Max Activating Token Index: 358