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

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

Neuron 4478 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6725. Min Range: -2.6725

Max Act: 2.6725. Min Act: -0.0000

Data Index: 1011424 (C4 (Web Text))

Max Activating Token Index: 800

Text #1

Max Range: 2.6725. Min Range: -2.6725

Max Act: 2.6484. Min Act: -0.0000

Data Index: 751096 (C4 (Web Text))

Max Activating Token Index: 425

Text #2

Max Range: 2.6725. Min Range: -2.6725

Max Act: 2.6073. Min Act: -0.0000

Data Index: 290038 (C4 (Web Text))

Max Activating Token Index: 815

Text #3

Max Range: 2.6725. Min Range: -2.6725

Max Act: 2.5008. Min Act: -0.0000

Data Index: 264397 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 2.6725. Min Range: -2.6725

Max Act: 2.4962. Min Act: -0.0000

Data Index: 906785 (C4 (Web Text))

Max Activating Token Index: 632

Text #5

Max Range: 2.6725. Min Range: -2.6725

Max Act: 2.3564. Min Act: -0.0000

Data Index: 582321 (C4 (Web Text))

Max Activating Token Index: 341

Text #6

Max Range: 2.6725. Min Range: -2.6725

Max Act: 2.2881. Min Act: -0.0000

Data Index: 212322 (C4 (Web Text))

Max Activating Token Index: 165

Text #7

Max Range: 2.6725. Min Range: -2.6725

Max Act: 2.2886. Min Act: -0.0000

Data Index: 1046833 (C4 (Web Text))

Max Activating Token Index: 253

Text #8

Max Range: 2.6725. Min Range: -2.6725

Max Act: 2.2511. Min Act: -0.0000

Data Index: 857141 (C4 (Web Text))

Max Activating Token Index: 859

Text #9

Max Range: 2.6725. Min Range: -2.6725

Max Act: 2.1958. Min Act: -0.0000

Data Index: 405247 (C4 (Web Text))

Max Activating Token Index: 600

Text #10

Max Range: 2.6725. Min Range: -2.6725

Max Act: 2.1654. Min Act: -0.0000

Data Index: 479054 (C4 (Web Text))

Max Activating Token Index: 567

Text #11

Max Range: 2.6725. Min Range: -2.6725

Max Act: 2.1657. Min Act: -0.0000

Data Index: 51835 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 2.6725. Min Range: -2.6725

Max Act: 2.0212. Min Act: -0.0000

Data Index: 192360 (C4 (Web Text))

Max Activating Token Index: 561

Text #13

Max Range: 2.6725. Min Range: -2.6725

Max Act: 2.1348. Min Act: -0.0000

Data Index: 608215 (C4 (Web Text))

Max Activating Token Index: 985

Text #14

Max Range: 2.6725. Min Range: -2.6725

Max Act: 2.0305. Min Act: -0.0000

Data Index: 105622 (C4 (Web Text))

Max Activating Token Index: 545

Text #15

Max Range: 2.6725. Min Range: -2.6725

Max Act: 1.9117. Min Act: -0.0000

Data Index: 283575 (C4 (Web Text))

Max Activating Token Index: 295

Text #16

Max Range: 2.6725. Min Range: -2.6725

Max Act: 1.8059. Min Act: -0.0000

Data Index: 1034721 (C4 (Web Text))

Max Activating Token Index: 958

Text #17

Max Range: 2.6725. Min Range: -2.6725

Max Act: 1.8776. Min Act: -0.0000

Data Index: 2689 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 2.6725. Min Range: -2.6725

Max Act: 1.8129. Min Act: -0.0000

Data Index: 1104596 (C4 (Web Text))

Max Activating Token Index: 255

Text #19

Max Range: 2.6725. Min Range: -2.6725

Max Act: 1.8123. Min Act: -0.0000

Data Index: 1190519 (C4 (Web Text))

Max Activating Token Index: 833