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

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

Neuron 2872 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5813. Min Range: -1.5813

Max Act: 1.5813. Min Act: -0.0001

Data Index: 691867 (C4 (Web Text))

Max Activating Token Index: 631

Text #1

Max Range: 1.5813. Min Range: -1.5813

Max Act: 1.2074. Min Act: -0.0001

Data Index: 926817 (C4 (Web Text))

Max Activating Token Index: 1015

Text #2

Max Range: 1.5813. Min Range: -1.5813

Max Act: 1.1272. Min Act: -0.0001

Data Index: 1178139 (C4 (Web Text))

Max Activating Token Index: 406

Text #3

Max Range: 1.5813. Min Range: -1.5813

Max Act: 1.1226. Min Act: -0.0001

Data Index: 23837 (C4 (Web Text))

Max Activating Token Index: 101

Text #4

Max Range: 1.5813. Min Range: -1.5813

Max Act: 1.1099. Min Act: -0.0001

Data Index: 139778 (C4 (Web Text))

Max Activating Token Index: 159

Text #5

Max Range: 1.5813. Min Range: -1.5813

Max Act: 1.1369. Min Act: -0.0001

Data Index: 799157 (C4 (Web Text))

Max Activating Token Index: 829

Text #6

Max Range: 1.5813. Min Range: -1.5813

Max Act: 1.1034. Min Act: -0.0001

Data Index: 787338 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 1.5813. Min Range: -1.5813

Max Act: 1.0862. Min Act: -0.0001

Data Index: 269360 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 1.5813. Min Range: -1.5813

Max Act: 1.1222. Min Act: -0.0001

Data Index: 391620 (C4 (Web Text))

Max Activating Token Index: 974

Text #9

Max Range: 1.5813. Min Range: -1.5813

Max Act: 1.0467. Min Act: -0.0001

Data Index: 1331548 (C4 (Web Text))

Max Activating Token Index: 667

Text #10

Max Range: 1.5813. Min Range: -1.5813

Max Act: 1.0684. Min Act: -0.0001

Data Index: 828765 (C4 (Web Text))

Max Activating Token Index: 629

Text #11

Max Range: 1.5813. Min Range: -1.5813

Max Act: 1.0383. Min Act: -0.0001

Data Index: 299465 (C4 (Web Text))

Max Activating Token Index: 815

Text #12

Max Range: 1.5813. Min Range: -1.5813

Max Act: 1.1274. Min Act: -0.0001

Data Index: 1209886 (C4 (Web Text))

Max Activating Token Index: 821

Text #13

Max Range: 1.5813. Min Range: -1.5813

Max Act: 1.0190. Min Act: -0.0001

Data Index: 461436 (C4 (Web Text))

Max Activating Token Index: 340

Text #14

Max Range: 1.5813. Min Range: -1.5813

Max Act: 1.0822. Min Act: -0.0001

Data Index: 1146883 (C4 (Web Text))

Max Activating Token Index: 492

Text #15

Max Range: 1.5813. Min Range: -1.5813

Max Act: 1.0407. Min Act: -0.0001

Data Index: 472155 (C4 (Web Text))

Max Activating Token Index: 352

Text #16

Max Range: 1.5813. Min Range: -1.5813

Max Act: 1.0046. Min Act: -0.0001

Data Index: 53634 (C4 (Web Text))

Max Activating Token Index: 582

Text #17

Max Range: 1.5813. Min Range: -1.5813

Max Act: 1.0323. Min Act: -0.0001

Data Index: 726992 (C4 (Web Text))

Max Activating Token Index: 163

Text #18

Max Range: 1.5813. Min Range: -1.5813

Max Act: 1.0283. Min Act: -0.0001

Data Index: 367906 (C4 (Web Text))

Max Activating Token Index: 977

Text #19

Max Range: 1.5813. Min Range: -1.5813

Max Act: 1.0294. Min Act: -0.0001

Data Index: 143438 (C4 (Web Text))

Max Activating Token Index: 300