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

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

Neuron 2115 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7759. Min Range: -1.7759

Max Act: 1.5152. Min Act: -0.0002

Data Index: 676693 (C4 (Web Text))

Max Activating Token Index: 849

Text #1

Max Range: 1.7759. Min Range: -1.7759

Max Act: 1.6059. Min Act: -0.0002

Data Index: 639852 (C4 (Web Text))

Max Activating Token Index: 844

Text #2

Max Range: 1.7759. Min Range: -1.7759

Max Act: 1.5439. Min Act: -0.0002

Data Index: 17943 (C4 (Web Text))

Max Activating Token Index: 846

Text #3

Max Range: 1.7759. Min Range: -1.7759

Max Act: 1.6780. Min Act: -0.0002

Data Index: 592714 (C4 (Web Text))

Max Activating Token Index: 947

Text #4

Max Range: 1.7759. Min Range: -1.7759

Max Act: 1.7759. Min Act: -0.0002

Data Index: 884917 (C4 (Web Text))

Max Activating Token Index: 232

Text #5

Max Range: 1.7759. Min Range: -1.7759

Max Act: 1.5419. Min Act: -0.0002

Data Index: 568840 (C4 (Web Text))

Max Activating Token Index: 126

Text #6

Max Range: 1.7759. Min Range: -1.7759

Max Act: 1.5416. Min Act: -0.0002

Data Index: 847169 (C4 (Web Text))

Max Activating Token Index: 925

Text #7

Max Range: 1.7759. Min Range: -1.7759

Max Act: 1.5498. Min Act: -0.0002

Data Index: 25233 (C4 (Web Text))

Max Activating Token Index: 53

Text #8

Max Range: 1.7759. Min Range: -1.7759

Max Act: 1.5353. Min Act: -0.0002

Data Index: 1179621 (C4 (Web Text))

Max Activating Token Index: 691

Text #9

Max Range: 1.7759. Min Range: -1.7759

Max Act: 1.5285. Min Act: -0.0002

Data Index: 1292771 (C4 (Web Text))

Max Activating Token Index: 1006

Text #10

Max Range: 1.7759. Min Range: -1.7759

Max Act: 1.7323. Min Act: -0.0002

Data Index: 362738 (C4 (Web Text))

Max Activating Token Index: 62

Text #11

Max Range: 1.7759. Min Range: -1.7759

Max Act: 1.5543. Min Act: -0.0002

Data Index: 465820 (C4 (Web Text))

Max Activating Token Index: 330

Text #12

Max Range: 1.7759. Min Range: -1.7759

Max Act: 1.5351. Min Act: -0.0002

Data Index: 562185 (C4 (Web Text))

Max Activating Token Index: 200

Text #13

Max Range: 1.7759. Min Range: -1.7759

Max Act: 1.7274. Min Act: -0.0002

Data Index: 822613 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 1.7759. Min Range: -1.7759

Max Act: 1.2736. Min Act: -0.0002

Data Index: 535812 (C4 (Web Text))

Max Activating Token Index: 175

Text #15

Max Range: 1.7759. Min Range: -1.7759

Max Act: 1.6206. Min Act: -0.0002

Data Index: 1075225 (C4 (Web Text))

Max Activating Token Index: 636

Text #16

Max Range: 1.7759. Min Range: -1.7759

Max Act: 1.6211. Min Act: -0.0002

Data Index: 779403 (C4 (Web Text))

Max Activating Token Index: 676

Text #17

Max Range: 1.7759. Min Range: -1.7759

Max Act: 1.5739. Min Act: -0.0002

Data Index: 945129 (C4 (Web Text))

Max Activating Token Index: 113

Text #18

Max Range: 1.7759. Min Range: -1.7759

Max Act: 1.5199. Min Act: -0.0002

Data Index: 1167081 (C4 (Web Text))

Max Activating Token Index: 823

Text #19

Max Range: 1.7759. Min Range: -1.7759

Max Act: 1.6304. Min Act: -0.0002

Data Index: 1326962 (C4 (Web Text))

Max Activating Token Index: 166