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

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

Neuron 88 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.9354. Min Range: -1.9354

Max Act: 1.9354. Min Act: -0.0002

Data Index: 94194 (C4 (Web Text))

Max Activating Token Index: 198

Text #1

Max Range: 1.9354. Min Range: -1.9354

Max Act: 1.7158. Min Act: -0.0002

Data Index: 333330 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 1.9354. Min Range: -1.9354

Max Act: 1.6649. Min Act: -0.0002

Data Index: 1352174 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 1.9354. Min Range: -1.9354

Max Act: 1.6698. Min Act: -0.0002

Data Index: 65491 (C4 (Web Text))

Max Activating Token Index: 292

Text #4

Max Range: 1.9354. Min Range: -1.9354

Max Act: 1.6313. Min Act: -0.0002

Data Index: 336897 (C4 (Web Text))

Max Activating Token Index: 1018

Text #5

Max Range: 1.9354. Min Range: -1.9354

Max Act: 1.5783. Min Act: -0.0002

Data Index: 1198424 (C4 (Web Text))

Max Activating Token Index: 400

Text #6

Max Range: 1.9354. Min Range: -1.9354

Max Act: 1.5760. Min Act: -0.0002

Data Index: 1152661 (C4 (Web Text))

Max Activating Token Index: 990

Text #7

Max Range: 1.9354. Min Range: -1.9354

Max Act: 1.5603. Min Act: -0.0002

Data Index: 401484 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 1.9354. Min Range: -1.9354

Max Act: 1.5557. Min Act: -0.0002

Data Index: 1165581 (C4 (Web Text))

Max Activating Token Index: 132

Text #9

Max Range: 1.9354. Min Range: -1.9354

Max Act: 1.5599. Min Act: -0.0002

Data Index: 13605 (C4 (Web Text))

Max Activating Token Index: 202

Text #10

Max Range: 1.9354. Min Range: -1.9354

Max Act: 1.5541. Min Act: -0.0002

Data Index: 302162 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 1.9354. Min Range: -1.9354

Max Act: 1.5272. Min Act: -0.0002

Data Index: 11965 (C4 (Web Text))

Max Activating Token Index: 896

Text #12

Max Range: 1.9354. Min Range: -1.9354

Max Act: 1.5436. Min Act: -0.0002

Data Index: 704718 (C4 (Web Text))

Max Activating Token Index: 989

Text #13

Max Range: 1.9354. Min Range: -1.9354

Max Act: 1.4908. Min Act: -0.0002

Data Index: 1106976 (C4 (Web Text))

Max Activating Token Index: 231

Text #14

Max Range: 1.9354. Min Range: -1.9354

Max Act: 1.4880. Min Act: -0.0002

Data Index: 425488 (C4 (Web Text))

Max Activating Token Index: 149

Text #15

Max Range: 1.9354. Min Range: -1.9354

Max Act: 1.4664. Min Act: -0.0002

Data Index: 239912 (C4 (Web Text))

Max Activating Token Index: 818

Text #16

Max Range: 1.9354. Min Range: -1.9354

Max Act: 1.4646. Min Act: -0.0002

Data Index: 829323 (C4 (Web Text))

Max Activating Token Index: 725

Text #17

Max Range: 1.9354. Min Range: -1.9354

Max Act: 1.4427. Min Act: -0.0002

Data Index: 1321860 (C4 (Web Text))

Max Activating Token Index: 110

Text #18

Max Range: 1.9354. Min Range: -1.9354

Max Act: 1.4869. Min Act: -0.0002

Data Index: 320804 (C4 (Web Text))

Max Activating Token Index: 977

Text #19

Max Range: 1.9354. Min Range: -1.9354

Max Act: 1.4727. Min Act: -0.0002

Data Index: 144202 (C4 (Web Text))

Max Activating Token Index: 322