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

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

Neuron 1677 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: 3.6724. Min Range: -3.6724

Max Act: 3.6724. Min Act: -0.0000

Data Index: 754375 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 3.6724. Min Range: -3.6724

Max Act: 2.5616. Min Act: -0.0000

Data Index: 1275968 (C4 (Web Text))

Max Activating Token Index: 182

Text #2

Max Range: 3.6724. Min Range: -3.6724

Max Act: 2.4634. Min Act: -0.0000

Data Index: 250220 (C4 (Web Text))

Max Activating Token Index: 52

Text #3

Max Range: 3.6724. Min Range: -3.6724

Max Act: 2.2053. Min Act: -0.0000

Data Index: 883458 (C4 (Web Text))

Max Activating Token Index: 514

Text #4

Max Range: 3.6724. Min Range: -3.6724

Max Act: 2.3838. Min Act: -0.0000

Data Index: 660761 (C4 (Web Text))

Max Activating Token Index: 105

Text #5

Max Range: 3.6724. Min Range: -3.6724

Max Act: 2.2396. Min Act: -0.0000

Data Index: 1193320 (C4 (Web Text))

Max Activating Token Index: 298

Text #6

Max Range: 3.6724. Min Range: -3.6724

Max Act: 2.0846. Min Act: -0.0000

Data Index: 794665 (C4 (Web Text))

Max Activating Token Index: 587

Text #7

Max Range: 3.6724. Min Range: -3.6724

Max Act: 2.0404. Min Act: -0.0000

Data Index: 295170 (C4 (Web Text))

Max Activating Token Index: 577

Text #8

Max Range: 3.6724. Min Range: -3.6724

Max Act: 2.2551. Min Act: -0.0000

Data Index: 563832 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 3.6724. Min Range: -3.6724

Max Act: 2.0167. Min Act: -0.0000

Data Index: 474695 (C4 (Web Text))

Max Activating Token Index: 615

Text #10

Max Range: 3.6724. Min Range: -3.6724

Max Act: 2.2326. Min Act: -0.0000

Data Index: 372204 (C4 (Web Text))

Max Activating Token Index: 61

Text #11

Max Range: 3.6724. Min Range: -3.6724

Max Act: 2.1012. Min Act: -0.0000

Data Index: 1054491 (C4 (Web Text))

Max Activating Token Index: 253

Text #12

Max Range: 3.6724. Min Range: -3.6724

Max Act: 2.0904. Min Act: -0.0000

Data Index: 1042330 (C4 (Web Text))

Max Activating Token Index: 410

Text #13

Max Range: 3.6724. Min Range: -3.6724

Max Act: 1.9173. Min Act: -0.0000

Data Index: 290544 (C4 (Web Text))

Max Activating Token Index: 154

Text #14

Max Range: 3.6724. Min Range: -3.6724

Max Act: 2.0027. Min Act: -0.0000

Data Index: 389777 (C4 (Web Text))

Max Activating Token Index: 198

Text #15

Max Range: 3.6724. Min Range: -3.6724

Max Act: 2.2157. Min Act: -0.0000

Data Index: 763021 (C4 (Web Text))

Max Activating Token Index: 124

Text #16

Max Range: 3.6724. Min Range: -3.6724

Max Act: 2.0799. Min Act: -0.0000

Data Index: 645765 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 3.6724. Min Range: -3.6724

Max Act: 2.0682. Min Act: -0.0000

Data Index: 1064499 (C4 (Web Text))

Max Activating Token Index: 65

Text #18

Max Range: 3.6724. Min Range: -3.6724

Max Act: 2.1422. Min Act: -0.0000

Data Index: 890891 (C4 (Web Text))

Max Activating Token Index: 161

Text #19

Max Range: 3.6724. Min Range: -3.6724

Max Act: 2.0436. Min Act: -0.0000

Data Index: 728993 (C4 (Web Text))

Max Activating Token Index: 19