Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1157 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0052. Min Act: -0.0005

Data Index: 1507328 (Python Code)

Max Activating Token Index: 914

Text #1

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0043. Min Act: -0.0006

Data Index: 1184997 (C4 (Web Text))

Max Activating Token Index: 852

Text #2

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0043. Min Act: -0.0005

Data Index: 1486559 (Python Code)

Max Activating Token Index: 662

Text #3

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0043. Min Act: -0.0006

Data Index: 553994 (C4 (Web Text))

Max Activating Token Index: 541

Text #4

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0042. Min Act: -0.0005

Data Index: 1584654 (Python Code)

Max Activating Token Index: 824

Text #5

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0041. Min Act: -0.0006

Data Index: 1153888 (C4 (Web Text))

Max Activating Token Index: 667

Text #6

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0041. Min Act: -0.0005

Data Index: 1517478 (Python Code)

Max Activating Token Index: 650

Text #7

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0040. Min Act: -0.0006

Data Index: 6054 (C4 (Web Text))

Max Activating Token Index: 802

Text #8

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0041. Min Act: -0.0005

Data Index: 401751 (C4 (Web Text))

Max Activating Token Index: 796

Text #9

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0040. Min Act: -0.0006

Data Index: 890001 (C4 (Web Text))

Max Activating Token Index: 530

Text #10

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0040. Min Act: -0.0005

Data Index: 1401263 (Python Code)

Max Activating Token Index: 560

Text #11

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0038. Min Act: -0.0006

Data Index: 999427 (C4 (Web Text))

Max Activating Token Index: 745

Text #12

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0040. Min Act: -0.0006

Data Index: 213689 (C4 (Web Text))

Max Activating Token Index: 826

Text #13

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0036. Min Act: -0.0005

Data Index: 1593155 (Python Code)

Max Activating Token Index: 714

Text #14

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0038. Min Act: -0.0005

Data Index: 1640422 (Python Code)

Max Activating Token Index: 583

Text #15

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0038. Min Act: -0.0005

Data Index: 1455564 (Python Code)

Max Activating Token Index: 842

Text #16

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0037. Min Act: -0.0006

Data Index: 1460463 (Python Code)

Max Activating Token Index: 722

Text #17

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0037. Min Act: -0.0005

Data Index: 62289 (C4 (Web Text))

Max Activating Token Index: 474

Text #18

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0037. Min Act: -0.0005

Data Index: 1642172 (Python Code)

Max Activating Token Index: 876

Text #19

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0038. Min Act: -0.0005

Data Index: 403144 (C4 (Web Text))

Max Activating Token Index: 819