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

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

Neuron 4557 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: 0.1326. Min Range: -0.1326

Max Act: 0.1304. Min Act: -0.0000

Data Index: 8844 (C4 (Web Text))

Max Activating Token Index: 74

Text #1

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.1326. Min Act: -0.0000

Data Index: 1091957 (C4 (Web Text))

Max Activating Token Index: 864

Text #2

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.1282. Min Act: -0.0000

Data Index: 600530 (C4 (Web Text))

Max Activating Token Index: 465

Text #3

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.1180. Min Act: -0.0000

Data Index: 41044 (C4 (Web Text))

Max Activating Token Index: 702

Text #4

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.1134. Min Act: -0.0000

Data Index: 1163243 (C4 (Web Text))

Max Activating Token Index: 978

Text #5

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.1055. Min Act: -0.0000

Data Index: 917806 (C4 (Web Text))

Max Activating Token Index: 382

Text #6

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.1036. Min Act: -0.0000

Data Index: 832912 (C4 (Web Text))

Max Activating Token Index: 338

Text #7

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.0967. Min Act: -0.0000

Data Index: 1124083 (C4 (Web Text))

Max Activating Token Index: 163

Text #8

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.1027. Min Act: -0.0000

Data Index: 130318 (C4 (Web Text))

Max Activating Token Index: 957

Text #9

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.0893. Min Act: -0.0000

Data Index: 183865 (C4 (Web Text))

Max Activating Token Index: 713

Text #10

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.1080. Min Act: -0.0000

Data Index: 924538 (C4 (Web Text))

Max Activating Token Index: 805

Text #11

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.1000. Min Act: -0.0000

Data Index: 1339490 (C4 (Web Text))

Max Activating Token Index: 505

Text #12

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.0959. Min Act: -0.0000

Data Index: 847146 (C4 (Web Text))

Max Activating Token Index: 775

Text #13

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.0988. Min Act: -0.0000

Data Index: 1210048 (C4 (Web Text))

Max Activating Token Index: 153

Text #14

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.0946. Min Act: -0.0000

Data Index: 673586 (C4 (Web Text))

Max Activating Token Index: 51

Text #15

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.0874. Min Act: -0.0000

Data Index: 764478 (C4 (Web Text))

Max Activating Token Index: 868

Text #16

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.0917. Min Act: -0.0000

Data Index: 222002 (C4 (Web Text))

Max Activating Token Index: 208

Text #17

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.0921. Min Act: -0.0000

Data Index: 199893 (C4 (Web Text))

Max Activating Token Index: 604

Text #18

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.0850. Min Act: -0.0000

Data Index: 586494 (C4 (Web Text))

Max Activating Token Index: 604

Text #19

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.0936. Min Act: -0.0000

Data Index: 444375 (C4 (Web Text))

Max Activating Token Index: 731