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

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

Neuron 3095 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0579. Min Range: -1.0579

Max Act: 1.0538. Min Act: -0.0000

Data Index: 831068 (C4 (Web Text))

Max Activating Token Index: 976

Text #1

Max Range: 1.0579. Min Range: -1.0579

Max Act: 1.0579. Min Act: -0.0001

Data Index: 1064127 (C4 (Web Text))

Max Activating Token Index: 825

Text #2

Max Range: 1.0579. Min Range: -1.0579

Max Act: 0.9194. Min Act: -0.0001

Data Index: 786493 (C4 (Web Text))

Max Activating Token Index: 328

Text #3

Max Range: 1.0579. Min Range: -1.0579

Max Act: 0.8235. Min Act: -0.0001

Data Index: 610043 (C4 (Web Text))

Max Activating Token Index: 574

Text #4

Max Range: 1.0579. Min Range: -1.0579

Max Act: 0.7755. Min Act: -0.0001

Data Index: 1326575 (C4 (Web Text))

Max Activating Token Index: 591

Text #5

Max Range: 1.0579. Min Range: -1.0579

Max Act: 0.7725. Min Act: -0.0000

Data Index: 759763 (C4 (Web Text))

Max Activating Token Index: 412

Text #6

Max Range: 1.0579. Min Range: -1.0579

Max Act: 0.8202. Min Act: -0.0000

Data Index: 392395 (C4 (Web Text))

Max Activating Token Index: 238

Text #7

Max Range: 1.0579. Min Range: -1.0579

Max Act: 0.7871. Min Act: -0.0000

Data Index: 953538 (C4 (Web Text))

Max Activating Token Index: 765

Text #8

Max Range: 1.0579. Min Range: -1.0579

Max Act: 0.8059. Min Act: -0.0001

Data Index: 1207391 (C4 (Web Text))

Max Activating Token Index: 859

Text #9

Max Range: 1.0579. Min Range: -1.0579

Max Act: 0.7621. Min Act: -0.0000

Data Index: 703490 (C4 (Web Text))

Max Activating Token Index: 70

Text #10

Max Range: 1.0579. Min Range: -1.0579

Max Act: 0.7721. Min Act: -0.0000

Data Index: 824691 (C4 (Web Text))

Max Activating Token Index: 160

Text #11

Max Range: 1.0579. Min Range: -1.0579

Max Act: 0.7306. Min Act: -0.0000

Data Index: 767679 (C4 (Web Text))

Max Activating Token Index: 595

Text #12

Max Range: 1.0579. Min Range: -1.0579

Max Act: 0.7160. Min Act: -0.0000

Data Index: 306094 (C4 (Web Text))

Max Activating Token Index: 190

Text #13

Max Range: 1.0579. Min Range: -1.0579

Max Act: 0.6949. Min Act: -0.0001

Data Index: 878355 (C4 (Web Text))

Max Activating Token Index: 748

Text #14

Max Range: 1.0579. Min Range: -1.0579

Max Act: 0.7186. Min Act: -0.0000

Data Index: 380550 (C4 (Web Text))

Max Activating Token Index: 823

Text #15

Max Range: 1.0579. Min Range: -1.0579

Max Act: 0.6769. Min Act: -0.0000

Data Index: 363483 (C4 (Web Text))

Max Activating Token Index: 988

Text #16

Max Range: 1.0579. Min Range: -1.0579

Max Act: 0.6676. Min Act: -0.0000

Data Index: 1210177 (C4 (Web Text))

Max Activating Token Index: 221

Text #17

Max Range: 1.0579. Min Range: -1.0579

Max Act: 0.7033. Min Act: -0.0001

Data Index: 1342542 (C4 (Web Text))

Max Activating Token Index: 521

Text #18

Max Range: 1.0579. Min Range: -1.0579

Max Act: 0.6785. Min Act: -0.0000

Data Index: 330210 (C4 (Web Text))

Max Activating Token Index: 958

Text #19

Max Range: 1.0579. Min Range: -1.0579

Max Act: 0.6589. Min Act: -0.0001

Data Index: 1131899 (C4 (Web Text))

Max Activating Token Index: 951