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

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

Neuron 4036 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2819. Min Act: -0.0000

Data Index: 901503 (C4 (Web Text))

Max Activating Token Index: 814

Text #1

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2394. Min Act: -0.0000

Data Index: 1155118 (C4 (Web Text))

Max Activating Token Index: 201

Text #2

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2644. Min Act: -0.0000

Data Index: 779836 (C4 (Web Text))

Max Activating Token Index: 253

Text #3

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2448. Min Act: -0.0000

Data Index: 1059258 (C4 (Web Text))

Max Activating Token Index: 734

Text #4

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2421. Min Act: -0.0000

Data Index: 955325 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2309. Min Act: -0.0000

Data Index: 814770 (C4 (Web Text))

Max Activating Token Index: 541

Text #6

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2371. Min Act: -0.0000

Data Index: 468811 (C4 (Web Text))

Max Activating Token Index: 623

Text #7

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2303. Min Act: -0.0000

Data Index: 237266 (C4 (Web Text))

Max Activating Token Index: 496

Text #8

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2291. Min Act: -0.0000

Data Index: 1009552 (C4 (Web Text))

Max Activating Token Index: 462

Text #9

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2218. Min Act: -0.0000

Data Index: 72039 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2198. Min Act: -0.0000

Data Index: 918610 (C4 (Web Text))

Max Activating Token Index: 41

Text #11

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2194. Min Act: -0.0000

Data Index: 452169 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.1998. Min Act: -0.0000

Data Index: 816885 (C4 (Web Text))

Max Activating Token Index: 102

Text #13

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2195. Min Act: -0.0000

Data Index: 970071 (C4 (Web Text))

Max Activating Token Index: 776

Text #14

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2164. Min Act: -0.0000

Data Index: 1346386 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2136. Min Act: -0.0000

Data Index: 96899 (C4 (Web Text))

Max Activating Token Index: 126

Text #16

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.1973. Min Act: -0.0000

Data Index: 900970 (C4 (Web Text))

Max Activating Token Index: 520

Text #17

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2126. Min Act: -0.0000

Data Index: 353495 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.1939. Min Act: -0.0000

Data Index: 697143 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2053. Min Act: -0.0000

Data Index: 1216740 (C4 (Web Text))

Max Activating Token Index: 833