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

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

Neuron 1736 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2923. Min Range: -1.2923

Max Act: 1.2923. Min Act: -0.0001

Data Index: 950155 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 1.2923. Min Range: -1.2923

Max Act: 1.2397. Min Act: -0.0001

Data Index: 791861 (C4 (Web Text))

Max Activating Token Index: 508

Text #2

Max Range: 1.2923. Min Range: -1.2923

Max Act: 1.1857. Min Act: -0.0001

Data Index: 389831 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 1.2923. Min Range: -1.2923

Max Act: 1.1554. Min Act: -0.0001

Data Index: 244931 (C4 (Web Text))

Max Activating Token Index: 76

Text #4

Max Range: 1.2923. Min Range: -1.2923

Max Act: 0.9808. Min Act: -0.0001

Data Index: 956182 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 1.2923. Min Range: -1.2923

Max Act: 1.2206. Min Act: -0.0001

Data Index: 1138941 (C4 (Web Text))

Max Activating Token Index: 456

Text #6

Max Range: 1.2923. Min Range: -1.2923

Max Act: 1.1452. Min Act: -0.0001

Data Index: 1106578 (C4 (Web Text))

Max Activating Token Index: 602

Text #7

Max Range: 1.2923. Min Range: -1.2923

Max Act: 1.1350. Min Act: -0.0001

Data Index: 31372 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 1.2923. Min Range: -1.2923

Max Act: 1.1194. Min Act: -0.0001

Data Index: 1088349 (C4 (Web Text))

Max Activating Token Index: 1015

Text #9

Max Range: 1.2923. Min Range: -1.2923

Max Act: 1.1018. Min Act: -0.0001

Data Index: 635709 (C4 (Web Text))

Max Activating Token Index: 455

Text #10

Max Range: 1.2923. Min Range: -1.2923

Max Act: 1.0704. Min Act: -0.0001

Data Index: 88752 (C4 (Web Text))

Max Activating Token Index: 39

Text #11

Max Range: 1.2923. Min Range: -1.2923

Max Act: 1.0683. Min Act: -0.0001

Data Index: 289780 (C4 (Web Text))

Max Activating Token Index: 339

Text #12

Max Range: 1.2923. Min Range: -1.2923

Max Act: 0.9352. Min Act: -0.0001

Data Index: 359033 (C4 (Web Text))

Max Activating Token Index: 550

Text #13

Max Range: 1.2923. Min Range: -1.2923

Max Act: 1.0516. Min Act: -0.0001

Data Index: 1269014 (C4 (Web Text))

Max Activating Token Index: 568

Text #14

Max Range: 1.2923. Min Range: -1.2923

Max Act: 0.9787. Min Act: -0.0001

Data Index: 321015 (C4 (Web Text))

Max Activating Token Index: 884

Text #15

Max Range: 1.2923. Min Range: -1.2923

Max Act: 0.9733. Min Act: -0.0001

Data Index: 1359422 (C4 (Web Text))

Max Activating Token Index: 906

Text #16

Max Range: 1.2923. Min Range: -1.2923

Max Act: 1.0559. Min Act: -0.0001

Data Index: 15594 (C4 (Web Text))

Max Activating Token Index: 364

Text #17

Max Range: 1.2923. Min Range: -1.2923

Max Act: 0.9555. Min Act: -0.0001

Data Index: 21327 (C4 (Web Text))

Max Activating Token Index: 707

Text #18

Max Range: 1.2923. Min Range: -1.2923

Max Act: 0.9935. Min Act: -0.0001

Data Index: 638552 (C4 (Web Text))

Max Activating Token Index: 749

Text #19

Max Range: 1.2923. Min Range: -1.2923

Max Act: 1.0535. Min Act: -0.0001

Data Index: 676691 (C4 (Web Text))

Max Activating Token Index: 612