Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1953 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5109. Min Range: -1.5109

Max Act: 1.4303. Min Act: -0.0002

Data Index: 74758 (C4 (Web Text))

Max Activating Token Index: 425

Text #1

Max Range: 1.5109. Min Range: -1.5109

Max Act: 1.2487. Min Act: -0.0001

Data Index: 528453 (C4 (Web Text))

Max Activating Token Index: 739

Text #2

Max Range: 1.5109. Min Range: -1.5109

Max Act: 1.5109. Min Act: -0.0002

Data Index: 1035752 (C4 (Web Text))

Max Activating Token Index: 983

Text #3

Max Range: 1.5109. Min Range: -1.5109

Max Act: 1.3744. Min Act: -0.0002

Data Index: 330433 (C4 (Web Text))

Max Activating Token Index: 782

Text #4

Max Range: 1.5109. Min Range: -1.5109

Max Act: 1.4089. Min Act: -0.0002

Data Index: 469078 (C4 (Web Text))

Max Activating Token Index: 582

Text #5

Max Range: 1.5109. Min Range: -1.5109

Max Act: 1.3130. Min Act: -0.0002

Data Index: 50183 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 1.5109. Min Range: -1.5109

Max Act: 1.2273. Min Act: -0.0001

Data Index: 820076 (C4 (Web Text))

Max Activating Token Index: 138

Text #7

Max Range: 1.5109. Min Range: -1.5109

Max Act: 1.1867. Min Act: -0.0002

Data Index: 665529 (C4 (Web Text))

Max Activating Token Index: 963

Text #8

Max Range: 1.5109. Min Range: -1.5109

Max Act: 1.0482. Min Act: -0.0001

Data Index: 457410 (C4 (Web Text))

Max Activating Token Index: 233

Text #9

Max Range: 1.5109. Min Range: -1.5109

Max Act: 1.1321. Min Act: -0.0002

Data Index: 103224 (C4 (Web Text))

Max Activating Token Index: 371

Text #10

Max Range: 1.5109. Min Range: -1.5109

Max Act: 1.1744. Min Act: -0.0002

Data Index: 289121 (C4 (Web Text))

Max Activating Token Index: 657

Text #11

Max Range: 1.5109. Min Range: -1.5109

Max Act: 1.1664. Min Act: -0.0002

Data Index: 1106690 (C4 (Web Text))

Max Activating Token Index: 948

Text #12

Max Range: 1.5109. Min Range: -1.5109

Max Act: 1.1540. Min Act: -0.0001

Data Index: 1209200 (C4 (Web Text))

Max Activating Token Index: 957

Text #13

Max Range: 1.5109. Min Range: -1.5109

Max Act: 1.0486. Min Act: -0.0001

Data Index: 1232362 (C4 (Web Text))

Max Activating Token Index: 582

Text #14

Max Range: 1.5109. Min Range: -1.5109

Max Act: 1.1448. Min Act: -0.0002

Data Index: 314921 (C4 (Web Text))

Max Activating Token Index: 99

Text #15

Max Range: 1.5109. Min Range: -1.5109

Max Act: 1.1746. Min Act: -0.0002

Data Index: 772916 (C4 (Web Text))

Max Activating Token Index: 889

Text #16

Max Range: 1.5109. Min Range: -1.5109

Max Act: 1.1568. Min Act: -0.0002

Data Index: 700496 (C4 (Web Text))

Max Activating Token Index: 849

Text #17

Max Range: 1.5109. Min Range: -1.5109

Max Act: 1.0846. Min Act: -0.0001

Data Index: 691093 (C4 (Web Text))

Max Activating Token Index: 287

Text #18

Max Range: 1.5109. Min Range: -1.5109

Max Act: 1.0779. Min Act: -0.0002

Data Index: 883806 (C4 (Web Text))

Max Activating Token Index: 442

Text #19

Max Range: 1.5109. Min Range: -1.5109

Max Act: 1.0703. Min Act: -0.0001

Data Index: 1352262 (C4 (Web Text))

Max Activating Token Index: 442