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

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

Neuron 1535 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0506. Min Act: -0.0001

Data Index: 745324 (C4 (Web Text))

Max Activating Token Index: 849

Text #1

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0484. Min Act: -0.0002

Data Index: 491158 (C4 (Web Text))

Max Activating Token Index: 674

Text #2

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0466. Min Act: -0.0002

Data Index: 1189123 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0455. Min Act: -0.0002

Data Index: 1105547 (C4 (Web Text))

Max Activating Token Index: 754

Text #4

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0427. Min Act: -0.0002

Data Index: 880454 (C4 (Web Text))

Max Activating Token Index: 478

Text #5

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0335. Min Act: -0.0001

Data Index: 1562909 (Python Code)

Max Activating Token Index: 166

Text #6

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0313. Min Act: -0.0001

Data Index: 1403937 (Python Code)

Max Activating Token Index: 13

Text #7

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0313. Min Act: -0.0001

Data Index: 1575094 (Python Code)

Max Activating Token Index: 38

Text #8

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0285. Min Act: -0.0002

Data Index: 1049418 (C4 (Web Text))

Max Activating Token Index: 526

Text #9

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0312. Min Act: -0.0001

Data Index: 1427683 (Python Code)

Max Activating Token Index: 6

Text #10

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0299. Min Act: -0.0001

Data Index: 1429465 (Python Code)

Max Activating Token Index: 959

Text #11

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0312. Min Act: -0.0001

Data Index: 1374474 (Python Code)

Max Activating Token Index: 445

Text #12

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0296. Min Act: -0.0001

Data Index: 1564652 (Python Code)

Max Activating Token Index: 195

Text #13

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0285. Min Act: -0.0001

Data Index: 752356 (C4 (Web Text))

Max Activating Token Index: 696

Text #14

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0292. Min Act: -0.0001

Data Index: 1553073 (Python Code)

Max Activating Token Index: 136

Text #15

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0294. Min Act: -0.0001

Data Index: 976160 (C4 (Web Text))

Max Activating Token Index: 650

Text #16

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0271. Min Act: -0.0001

Data Index: 1483834 (Python Code)

Max Activating Token Index: 162

Text #17

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0302. Min Act: -0.0001

Data Index: 1522144 (Python Code)

Max Activating Token Index: 961

Text #18

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0292. Min Act: -0.0001

Data Index: 1439186 (Python Code)

Max Activating Token Index: 128

Text #19

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0276. Min Act: -0.0001

Data Index: 686893 (C4 (Web Text))

Max Activating Token Index: 616