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

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

Neuron 4170 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.8732. Min Act: -0.0002

Data Index: 730766 (C4 (Web Text))

Max Activating Token Index: 81

Text #1

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.8021. Min Act: -0.0002

Data Index: 1144651 (C4 (Web Text))

Max Activating Token Index: 190

Text #2

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.7609. Min Act: -0.0002

Data Index: 975278 (C4 (Web Text))

Max Activating Token Index: 138

Text #3

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.7068. Min Act: -0.0002

Data Index: 762521 (C4 (Web Text))

Max Activating Token Index: 132

Text #4

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.7227. Min Act: -0.0002

Data Index: 1029301 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.7695. Min Act: -0.0002

Data Index: 187138 (C4 (Web Text))

Max Activating Token Index: 135

Text #6

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.7096. Min Act: -0.0002

Data Index: 580956 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.6778. Min Act: -0.0002

Data Index: 1028110 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.6742. Min Act: -0.0002

Data Index: 1318944 (C4 (Web Text))

Max Activating Token Index: 994

Text #9

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.6508. Min Act: -0.0002

Data Index: 887049 (C4 (Web Text))

Max Activating Token Index: 423

Text #10

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.6741. Min Act: -0.0002

Data Index: 772568 (C4 (Web Text))

Max Activating Token Index: 413

Text #11

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.6681. Min Act: -0.0002

Data Index: 481518 (C4 (Web Text))

Max Activating Token Index: 472

Text #12

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.6232. Min Act: -0.0002

Data Index: 1074002 (C4 (Web Text))

Max Activating Token Index: 533

Text #13

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.6776. Min Act: -0.0002

Data Index: 25322 (C4 (Web Text))

Max Activating Token Index: 275

Text #14

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.6523. Min Act: -0.0002

Data Index: 624954 (C4 (Web Text))

Max Activating Token Index: 648

Text #15

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.6309. Min Act: -0.0003

Data Index: 791439 (C4 (Web Text))

Max Activating Token Index: 77

Text #16

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.5877. Min Act: -0.0002

Data Index: 253278 (C4 (Web Text))

Max Activating Token Index: 310

Text #17

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.6454. Min Act: -0.0002

Data Index: 190088 (C4 (Web Text))

Max Activating Token Index: 42

Text #18

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.6205. Min Act: -0.0002

Data Index: 1311956 (C4 (Web Text))

Max Activating Token Index: 179

Text #19

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.6389. Min Act: -0.0002

Data Index: 37414 (C4 (Web Text))

Max Activating Token Index: 983