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

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

Neuron 3121 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5352. Min Range: -3.5352

Max Act: 3.5352. Min Act: -0.0000

Data Index: 1038669 (C4 (Web Text))

Max Activating Token Index: 223

Text #1

Max Range: 3.5352. Min Range: -3.5352

Max Act: 3.1996. Min Act: -0.0000

Data Index: 1038021 (C4 (Web Text))

Max Activating Token Index: 110

Text #2

Max Range: 3.5352. Min Range: -3.5352

Max Act: 3.1971. Min Act: -0.0000

Data Index: 224929 (C4 (Web Text))

Max Activating Token Index: 614

Text #3

Max Range: 3.5352. Min Range: -3.5352

Max Act: 3.1898. Min Act: -0.0000

Data Index: 821595 (C4 (Web Text))

Max Activating Token Index: 845

Text #4

Max Range: 3.5352. Min Range: -3.5352

Max Act: 3.0248. Min Act: -0.0000

Data Index: 1147052 (C4 (Web Text))

Max Activating Token Index: 790

Text #5

Max Range: 3.5352. Min Range: -3.5352

Max Act: 2.9485. Min Act: -0.0000

Data Index: 251068 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 3.5352. Min Range: -3.5352

Max Act: 3.0387. Min Act: -0.0000

Data Index: 1122965 (C4 (Web Text))

Max Activating Token Index: 42

Text #7

Max Range: 3.5352. Min Range: -3.5352

Max Act: 2.8741. Min Act: -0.0000

Data Index: 864735 (C4 (Web Text))

Max Activating Token Index: 951

Text #8

Max Range: 3.5352. Min Range: -3.5352

Max Act: 2.9558. Min Act: -0.0000

Data Index: 296933 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 3.5352. Min Range: -3.5352

Max Act: 2.6440. Min Act: -0.0000

Data Index: 89311 (C4 (Web Text))

Max Activating Token Index: 129

Text #10

Max Range: 3.5352. Min Range: -3.5352

Max Act: 2.7636. Min Act: -0.0000

Data Index: 136783 (C4 (Web Text))

Max Activating Token Index: 447

Text #11

Max Range: 3.5352. Min Range: -3.5352

Max Act: 2.5660. Min Act: -0.0000

Data Index: 554465 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 3.5352. Min Range: -3.5352

Max Act: 2.5728. Min Act: -0.0000

Data Index: 149431 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 3.5352. Min Range: -3.5352

Max Act: 2.5903. Min Act: -0.0000

Data Index: 525902 (C4 (Web Text))

Max Activating Token Index: 262

Text #14

Max Range: 3.5352. Min Range: -3.5352

Max Act: 2.5494. Min Act: -0.0000

Data Index: 1118203 (C4 (Web Text))

Max Activating Token Index: 416

Text #15

Max Range: 3.5352. Min Range: -3.5352

Max Act: 2.4214. Min Act: -0.0000

Data Index: 628256 (C4 (Web Text))

Max Activating Token Index: 417

Text #16

Max Range: 3.5352. Min Range: -3.5352

Max Act: 2.6636. Min Act: -0.0000

Data Index: 1128384 (C4 (Web Text))

Max Activating Token Index: 342

Text #17

Max Range: 3.5352. Min Range: -3.5352

Max Act: 2.4119. Min Act: -0.0000

Data Index: 60211 (C4 (Web Text))

Max Activating Token Index: 570

Text #18

Max Range: 3.5352. Min Range: -3.5352

Max Act: 2.6522. Min Act: -0.0000

Data Index: 1089203 (C4 (Web Text))

Max Activating Token Index: 404

Text #19

Max Range: 3.5352. Min Range: -3.5352

Max Act: 2.3733. Min Act: -0.0000

Data Index: 1268491 (C4 (Web Text))

Max Activating Token Index: 543