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

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

Neuron 437 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7030. Min Range: -1.7030

Max Act: 1.7030. Min Act: -0.0001

Data Index: 779825 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 1.7030. Min Range: -1.7030

Max Act: 1.4043. Min Act: -0.0001

Data Index: 13126 (C4 (Web Text))

Max Activating Token Index: 404

Text #2

Max Range: 1.7030. Min Range: -1.7030

Max Act: 1.3923. Min Act: -0.0001

Data Index: 1298209 (C4 (Web Text))

Max Activating Token Index: 720

Text #3

Max Range: 1.7030. Min Range: -1.7030

Max Act: 1.1836. Min Act: -0.0001

Data Index: 320908 (C4 (Web Text))

Max Activating Token Index: 874

Text #4

Max Range: 1.7030. Min Range: -1.7030

Max Act: 1.3318. Min Act: -0.0001

Data Index: 1240567 (C4 (Web Text))

Max Activating Token Index: 969

Text #5

Max Range: 1.7030. Min Range: -1.7030

Max Act: 1.3021. Min Act: -0.0001

Data Index: 621759 (C4 (Web Text))

Max Activating Token Index: 507

Text #6

Max Range: 1.7030. Min Range: -1.7030

Max Act: 1.1767. Min Act: -0.0001

Data Index: 174687 (C4 (Web Text))

Max Activating Token Index: 807

Text #7

Max Range: 1.7030. Min Range: -1.7030

Max Act: 1.1908. Min Act: -0.0001

Data Index: 87632 (C4 (Web Text))

Max Activating Token Index: 321

Text #8

Max Range: 1.7030. Min Range: -1.7030

Max Act: 1.1863. Min Act: -0.0001

Data Index: 889521 (C4 (Web Text))

Max Activating Token Index: 553

Text #9

Max Range: 1.7030. Min Range: -1.7030

Max Act: 1.1743. Min Act: -0.0001

Data Index: 804329 (C4 (Web Text))

Max Activating Token Index: 483

Text #10

Max Range: 1.7030. Min Range: -1.7030

Max Act: 1.1523. Min Act: -0.0001

Data Index: 411187 (C4 (Web Text))

Max Activating Token Index: 684

Text #11

Max Range: 1.7030. Min Range: -1.7030

Max Act: 1.0711. Min Act: -0.0001

Data Index: 802540 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 1.7030. Min Range: -1.7030

Max Act: 1.0531. Min Act: -0.0001

Data Index: 846963 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 1.7030. Min Range: -1.7030

Max Act: 1.0510. Min Act: -0.0001

Data Index: 1313042 (C4 (Web Text))

Max Activating Token Index: 594

Text #14

Max Range: 1.7030. Min Range: -1.7030

Max Act: 1.1055. Min Act: -0.0001

Data Index: 440478 (C4 (Web Text))

Max Activating Token Index: 267

Text #15

Max Range: 1.7030. Min Range: -1.7030

Max Act: 0.9895. Min Act: -0.0001

Data Index: 1124144 (C4 (Web Text))

Max Activating Token Index: 298

Text #16

Max Range: 1.7030. Min Range: -1.7030

Max Act: 0.9392. Min Act: -0.0001

Data Index: 1531642 (Python Code)

Max Activating Token Index: 42

Text #17

Max Range: 1.7030. Min Range: -1.7030

Max Act: 0.8326. Min Act: -0.0001

Data Index: 1484938 (Python Code)

Max Activating Token Index: 305

Text #18

Max Range: 1.7030. Min Range: -1.7030

Max Act: 0.9798. Min Act: -0.0001

Data Index: 736631 (C4 (Web Text))

Max Activating Token Index: 158

Text #19

Max Range: 1.7030. Min Range: -1.7030

Max Act: 0.9225. Min Act: -0.0001

Data Index: 1343350 (C4 (Web Text))

Max Activating Token Index: 72