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

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

Neuron 3706 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1192. Min Range: -1.1192

Max Act: 1.1192. Min Act: -0.0000

Data Index: 820231 (C4 (Web Text))

Max Activating Token Index: 129

Text #1

Max Range: 1.1192. Min Range: -1.1192

Max Act: 1.0846. Min Act: -0.0000

Data Index: 881268 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 1.1192. Min Range: -1.1192

Max Act: 1.0219. Min Act: -0.0000

Data Index: 61686 (C4 (Web Text))

Max Activating Token Index: 617

Text #3

Max Range: 1.1192. Min Range: -1.1192

Max Act: 0.9928. Min Act: -0.0000

Data Index: 1144655 (C4 (Web Text))

Max Activating Token Index: 638

Text #4

Max Range: 1.1192. Min Range: -1.1192

Max Act: 0.9870. Min Act: -0.0000

Data Index: 640251 (C4 (Web Text))

Max Activating Token Index: 485

Text #5

Max Range: 1.1192. Min Range: -1.1192

Max Act: 0.8963. Min Act: -0.0000

Data Index: 972676 (C4 (Web Text))

Max Activating Token Index: 719

Text #6

Max Range: 1.1192. Min Range: -1.1192

Max Act: 0.9474. Min Act: -0.0000

Data Index: 666035 (C4 (Web Text))

Max Activating Token Index: 578

Text #7

Max Range: 1.1192. Min Range: -1.1192

Max Act: 0.8831. Min Act: -0.0000

Data Index: 88609 (C4 (Web Text))

Max Activating Token Index: 101

Text #8

Max Range: 1.1192. Min Range: -1.1192

Max Act: 0.8694. Min Act: -0.0000

Data Index: 98631 (C4 (Web Text))

Max Activating Token Index: 594

Text #9

Max Range: 1.1192. Min Range: -1.1192

Max Act: 0.8575. Min Act: -0.0000

Data Index: 46784 (C4 (Web Text))

Max Activating Token Index: 229

Text #10

Max Range: 1.1192. Min Range: -1.1192

Max Act: 0.8301. Min Act: -0.0000

Data Index: 29861 (C4 (Web Text))

Max Activating Token Index: 540

Text #11

Max Range: 1.1192. Min Range: -1.1192

Max Act: 0.8804. Min Act: -0.0000

Data Index: 563086 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 1.1192. Min Range: -1.1192

Max Act: 0.8513. Min Act: -0.0000

Data Index: 152027 (C4 (Web Text))

Max Activating Token Index: 909

Text #13

Max Range: 1.1192. Min Range: -1.1192

Max Act: 0.8685. Min Act: -0.0000

Data Index: 1338626 (C4 (Web Text))

Max Activating Token Index: 610

Text #14

Max Range: 1.1192. Min Range: -1.1192

Max Act: 0.8523. Min Act: -0.0000

Data Index: 472938 (C4 (Web Text))

Max Activating Token Index: 678

Text #15

Max Range: 1.1192. Min Range: -1.1192

Max Act: 0.8514. Min Act: -0.0000

Data Index: 25933 (C4 (Web Text))

Max Activating Token Index: 295

Text #16

Max Range: 1.1192. Min Range: -1.1192

Max Act: 0.7977. Min Act: -0.0000

Data Index: 734628 (C4 (Web Text))

Max Activating Token Index: 707

Text #17

Max Range: 1.1192. Min Range: -1.1192

Max Act: 0.8333. Min Act: -0.0000

Data Index: 570013 (C4 (Web Text))

Max Activating Token Index: 864

Text #18

Max Range: 1.1192. Min Range: -1.1192

Max Act: 0.8125. Min Act: -0.0000

Data Index: 686216 (C4 (Web Text))

Max Activating Token Index: 802

Text #19

Max Range: 1.1192. Min Range: -1.1192

Max Act: 0.7834. Min Act: -0.0000

Data Index: 926828 (C4 (Web Text))

Max Activating Token Index: 451