Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 40 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.5667. Min Act: -0.0003

Data Index: 1262929 (C4 (Web Text))

Max Activating Token Index: 950

Text #1

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.5558. Min Act: -0.0003

Data Index: 83490 (C4 (Web Text))

Max Activating Token Index: 734

Text #2

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.5197. Min Act: -0.0003

Data Index: 875009 (C4 (Web Text))

Max Activating Token Index: 359

Text #3

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.5496. Min Act: -0.0003

Data Index: 480293 (C4 (Web Text))

Max Activating Token Index: 148

Text #4

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.5452. Min Act: -0.0003

Data Index: 951873 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.5769. Min Act: -0.0003

Data Index: 741942 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4874. Min Act: -0.0003

Data Index: 605472 (C4 (Web Text))

Max Activating Token Index: 987

Text #7

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.5703. Min Act: -0.0003

Data Index: 260661 (C4 (Web Text))

Max Activating Token Index: 861

Text #8

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.5337. Min Act: -0.0003

Data Index: 986040 (C4 (Web Text))

Max Activating Token Index: 78

Text #9

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.5310. Min Act: -0.0003

Data Index: 1296750 (C4 (Web Text))

Max Activating Token Index: 276

Text #10

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.5252. Min Act: -0.0003

Data Index: 367635 (C4 (Web Text))

Max Activating Token Index: 530

Text #11

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.5265. Min Act: -0.0003

Data Index: 553792 (C4 (Web Text))

Max Activating Token Index: 77

Text #12

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.5096. Min Act: -0.0003

Data Index: 1124824 (C4 (Web Text))

Max Activating Token Index: 264

Text #13

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.5223. Min Act: -0.0003

Data Index: 99117 (C4 (Web Text))

Max Activating Token Index: 123

Text #14

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4887. Min Act: -0.0003

Data Index: 694134 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.5340. Min Act: -0.0003

Data Index: 711818 (C4 (Web Text))

Max Activating Token Index: 212

Text #16

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.5702. Min Act: -0.0003

Data Index: 575156 (C4 (Web Text))

Max Activating Token Index: 823

Text #17

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.5008. Min Act: -0.0003

Data Index: 9769 (C4 (Web Text))

Max Activating Token Index: 423

Text #18

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4986. Min Act: -0.0003

Data Index: 763075 (C4 (Web Text))

Max Activating Token Index: 65

Text #19

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.5121. Min Act: -0.0003

Data Index: 1315759 (C4 (Web Text))

Max Activating Token Index: 848