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

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

Neuron 2392 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: 0.3058. Min Range: -0.3058

Max Act: 0.3058. Min Act: -0.0000

Data Index: 301300 (C4 (Web Text))

Max Activating Token Index: 113

Text #1

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2723. Min Act: -0.0000

Data Index: 1038355 (C4 (Web Text))

Max Activating Token Index: 54

Text #2

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2690. Min Act: -0.0000

Data Index: 165748 (C4 (Web Text))

Max Activating Token Index: 167

Text #3

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2398. Min Act: -0.0000

Data Index: 76017 (C4 (Web Text))

Max Activating Token Index: 145

Text #4

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2379. Min Act: -0.0000

Data Index: 1345290 (C4 (Web Text))

Max Activating Token Index: 809

Text #5

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2255. Min Act: -0.0000

Data Index: 986392 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2202. Min Act: -0.0001

Data Index: 782178 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2414. Min Act: -0.0000

Data Index: 193283 (C4 (Web Text))

Max Activating Token Index: 904

Text #8

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2175. Min Act: -0.0001

Data Index: 629867 (C4 (Web Text))

Max Activating Token Index: 766

Text #9

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2267. Min Act: -0.0000

Data Index: 554353 (C4 (Web Text))

Max Activating Token Index: 494

Text #10

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2180. Min Act: -0.0000

Data Index: 300684 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2229. Min Act: -0.0000

Data Index: 499394 (C4 (Web Text))

Max Activating Token Index: 998

Text #12

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2287. Min Act: -0.0000

Data Index: 1315880 (C4 (Web Text))

Max Activating Token Index: 881

Text #13

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2242. Min Act: -0.0000

Data Index: 5697 (C4 (Web Text))

Max Activating Token Index: 967

Text #14

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2075. Min Act: -0.0001

Data Index: 1192523 (C4 (Web Text))

Max Activating Token Index: 105

Text #15

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2130. Min Act: -0.0001

Data Index: 1226577 (C4 (Web Text))

Max Activating Token Index: 592

Text #16

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2025. Min Act: -0.0000

Data Index: 1153919 (C4 (Web Text))

Max Activating Token Index: 426

Text #17

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.1991. Min Act: -0.0000

Data Index: 709558 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.1922. Min Act: -0.0000

Data Index: 1254460 (C4 (Web Text))

Max Activating Token Index: 787

Text #19

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2015. Min Act: -0.0000

Data Index: 104716 (C4 (Web Text))

Max Activating Token Index: 330