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

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

Neuron 802 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2725. Min Range: -1.2725

Max Act: 1.2347. Min Act: -0.0000

Data Index: 647057 (C4 (Web Text))

Max Activating Token Index: 105

Text #1

Max Range: 1.2725. Min Range: -1.2725

Max Act: 1.2336. Min Act: -0.0000

Data Index: 367081 (C4 (Web Text))

Max Activating Token Index: 792

Text #2

Max Range: 1.2725. Min Range: -1.2725

Max Act: 1.2725. Min Act: -0.0000

Data Index: 692374 (C4 (Web Text))

Max Activating Token Index: 108

Text #3

Max Range: 1.2725. Min Range: -1.2725

Max Act: 1.0803. Min Act: -0.0000

Data Index: 58535 (C4 (Web Text))

Max Activating Token Index: 18

Text #4

Max Range: 1.2725. Min Range: -1.2725

Max Act: 1.0152. Min Act: -0.0000

Data Index: 1056806 (C4 (Web Text))

Max Activating Token Index: 970

Text #5

Max Range: 1.2725. Min Range: -1.2725

Max Act: 1.1484. Min Act: -0.0000

Data Index: 1313025 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 1.2725. Min Range: -1.2725

Max Act: 0.9443. Min Act: -0.0000

Data Index: 1240952 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 1.2725. Min Range: -1.2725

Max Act: 1.0550. Min Act: -0.0001

Data Index: 1420420 (Python Code)

Max Activating Token Index: 29

Text #8

Max Range: 1.2725. Min Range: -1.2725

Max Act: 1.0262. Min Act: -0.0000

Data Index: 1152954 (C4 (Web Text))

Max Activating Token Index: 39

Text #9

Max Range: 1.2725. Min Range: -1.2725

Max Act: 0.9979. Min Act: -0.0000

Data Index: 691276 (C4 (Web Text))

Max Activating Token Index: 300

Text #10

Max Range: 1.2725. Min Range: -1.2725

Max Act: 1.1134. Min Act: -0.0000

Data Index: 958883 (C4 (Web Text))

Max Activating Token Index: 812

Text #11

Max Range: 1.2725. Min Range: -1.2725

Max Act: 0.9142. Min Act: -0.0000

Data Index: 570694 (C4 (Web Text))

Max Activating Token Index: 972

Text #12

Max Range: 1.2725. Min Range: -1.2725

Max Act: 0.9477. Min Act: -0.0000

Data Index: 600671 (C4 (Web Text))

Max Activating Token Index: 65

Text #13

Max Range: 1.2725. Min Range: -1.2725

Max Act: 0.8899. Min Act: -0.0000

Data Index: 1174540 (C4 (Web Text))

Max Activating Token Index: 706

Text #14

Max Range: 1.2725. Min Range: -1.2725

Max Act: 0.9106. Min Act: -0.0000

Data Index: 616311 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 1.2725. Min Range: -1.2725

Max Act: 0.9382. Min Act: -0.0000

Data Index: 85624 (C4 (Web Text))

Max Activating Token Index: 397

Text #16

Max Range: 1.2725. Min Range: -1.2725

Max Act: 0.9427. Min Act: -0.0000

Data Index: 201659 (C4 (Web Text))

Max Activating Token Index: 907

Text #17

Max Range: 1.2725. Min Range: -1.2725

Max Act: 0.9613. Min Act: -0.0000

Data Index: 341349 (C4 (Web Text))

Max Activating Token Index: 804

Text #18

Max Range: 1.2725. Min Range: -1.2725

Max Act: 0.8413. Min Act: -0.0000

Data Index: 115031 (C4 (Web Text))

Max Activating Token Index: 915

Text #19

Max Range: 1.2725. Min Range: -1.2725

Max Act: 0.9325. Min Act: -0.0000

Data Index: 824746 (C4 (Web Text))

Max Activating Token Index: 37