Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 484 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.8048. Min Range: -2.8048

Max Act: 2.8048. Min Act: -0.0000

Data Index: 407580 (C4 (Web Text))

Max Activating Token Index: 817

Text #1

Max Range: 2.8048. Min Range: -2.8048

Max Act: 2.2322. Min Act: -0.0000

Data Index: 966272 (C4 (Web Text))

Max Activating Token Index: 733

Text #2

Max Range: 2.8048. Min Range: -2.8048

Max Act: 2.4664. Min Act: -0.0000

Data Index: 650661 (C4 (Web Text))

Max Activating Token Index: 203

Text #3

Max Range: 2.8048. Min Range: -2.8048

Max Act: 2.3145. Min Act: -0.0000

Data Index: 164331 (C4 (Web Text))

Max Activating Token Index: 389

Text #4

Max Range: 2.8048. Min Range: -2.8048

Max Act: 2.4204. Min Act: -0.0000

Data Index: 238814 (C4 (Web Text))

Max Activating Token Index: 464

Text #5

Max Range: 2.8048. Min Range: -2.8048

Max Act: 2.1442. Min Act: -0.0000

Data Index: 672454 (C4 (Web Text))

Max Activating Token Index: 967

Text #6

Max Range: 2.8048. Min Range: -2.8048

Max Act: 2.0838. Min Act: -0.0000

Data Index: 316146 (C4 (Web Text))

Max Activating Token Index: 925

Text #7

Max Range: 2.8048. Min Range: -2.8048

Max Act: 2.3042. Min Act: -0.0000

Data Index: 304931 (C4 (Web Text))

Max Activating Token Index: 880

Text #8

Max Range: 2.8048. Min Range: -2.8048

Max Act: 1.9673. Min Act: -0.0000

Data Index: 1211336 (C4 (Web Text))

Max Activating Token Index: 469

Text #9

Max Range: 2.8048. Min Range: -2.8048

Max Act: 1.9739. Min Act: -0.0000

Data Index: 300080 (C4 (Web Text))

Max Activating Token Index: 463

Text #10

Max Range: 2.8048. Min Range: -2.8048

Max Act: 1.9654. Min Act: -0.0000

Data Index: 1027527 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 2.8048. Min Range: -2.8048

Max Act: 2.1675. Min Act: -0.0000

Data Index: 1195863 (C4 (Web Text))

Max Activating Token Index: 715

Text #12

Max Range: 2.8048. Min Range: -2.8048

Max Act: 2.1705. Min Act: -0.0000

Data Index: 41668 (C4 (Web Text))

Max Activating Token Index: 60

Text #13

Max Range: 2.8048. Min Range: -2.8048

Max Act: 1.8398. Min Act: -0.0000

Data Index: 1103233 (C4 (Web Text))

Max Activating Token Index: 727

Text #14

Max Range: 2.8048. Min Range: -2.8048

Max Act: 2.1354. Min Act: -0.0000

Data Index: 931222 (C4 (Web Text))

Max Activating Token Index: 414

Text #15

Max Range: 2.8048. Min Range: -2.8048

Max Act: 2.0111. Min Act: -0.0000

Data Index: 1071359 (C4 (Web Text))

Max Activating Token Index: 125

Text #16

Max Range: 2.8048. Min Range: -2.8048

Max Act: 1.8534. Min Act: -0.0000

Data Index: 1177016 (C4 (Web Text))

Max Activating Token Index: 119

Text #17

Max Range: 2.8048. Min Range: -2.8048

Max Act: 1.8610. Min Act: -0.0000

Data Index: 1359520 (C4 (Web Text))

Max Activating Token Index: 484

Text #18

Max Range: 2.8048. Min Range: -2.8048

Max Act: 1.9375. Min Act: -0.0000

Data Index: 737853 (C4 (Web Text))

Max Activating Token Index: 553

Text #19

Max Range: 2.8048. Min Range: -2.8048

Max Act: 1.7791. Min Act: -0.0000

Data Index: 124502 (C4 (Web Text))

Max Activating Token Index: 670