Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3051 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0628. Min Range: -1.0628

Max Act: 1.0628. Min Act: -0.0000

Data Index: 460311 (C4 (Web Text))

Max Activating Token Index: 641

Text #1

Max Range: 1.0628. Min Range: -1.0628

Max Act: 1.0223. Min Act: -0.0000

Data Index: 6704 (C4 (Web Text))

Max Activating Token Index: 156

Text #2

Max Range: 1.0628. Min Range: -1.0628

Max Act: 0.9483. Min Act: -0.0000

Data Index: 790168 (C4 (Web Text))

Max Activating Token Index: 108

Text #3

Max Range: 1.0628. Min Range: -1.0628

Max Act: 1.0079. Min Act: -0.0000

Data Index: 1116624 (C4 (Web Text))

Max Activating Token Index: 38

Text #4

Max Range: 1.0628. Min Range: -1.0628

Max Act: 0.9896. Min Act: -0.0000

Data Index: 616118 (C4 (Web Text))

Max Activating Token Index: 562

Text #5

Max Range: 1.0628. Min Range: -1.0628

Max Act: 1.0263. Min Act: -0.0000

Data Index: 1347444 (C4 (Web Text))

Max Activating Token Index: 435

Text #6

Max Range: 1.0628. Min Range: -1.0628

Max Act: 0.9345. Min Act: -0.0000

Data Index: 138680 (C4 (Web Text))

Max Activating Token Index: 671

Text #7

Max Range: 1.0628. Min Range: -1.0628

Max Act: 0.9790. Min Act: -0.0000

Data Index: 125832 (C4 (Web Text))

Max Activating Token Index: 811

Text #8

Max Range: 1.0628. Min Range: -1.0628

Max Act: 0.9679. Min Act: -0.0000

Data Index: 334322 (C4 (Web Text))

Max Activating Token Index: 639

Text #9

Max Range: 1.0628. Min Range: -1.0628

Max Act: 0.9089. Min Act: -0.0000

Data Index: 613958 (C4 (Web Text))

Max Activating Token Index: 644

Text #10

Max Range: 1.0628. Min Range: -1.0628

Max Act: 0.9037. Min Act: -0.0000

Data Index: 458379 (C4 (Web Text))

Max Activating Token Index: 81

Text #11

Max Range: 1.0628. Min Range: -1.0628

Max Act: 0.8490. Min Act: -0.0000

Data Index: 12014 (C4 (Web Text))

Max Activating Token Index: 922

Text #12

Max Range: 1.0628. Min Range: -1.0628

Max Act: 0.8109. Min Act: -0.0000

Data Index: 592059 (C4 (Web Text))

Max Activating Token Index: 729

Text #13

Max Range: 1.0628. Min Range: -1.0628

Max Act: 0.8122. Min Act: -0.0000

Data Index: 862555 (C4 (Web Text))

Max Activating Token Index: 726

Text #14

Max Range: 1.0628. Min Range: -1.0628

Max Act: 0.8265. Min Act: -0.0000

Data Index: 1060451 (C4 (Web Text))

Max Activating Token Index: 859

Text #15

Max Range: 1.0628. Min Range: -1.0628

Max Act: 0.8137. Min Act: -0.0000

Data Index: 1354599 (C4 (Web Text))

Max Activating Token Index: 489

Text #16

Max Range: 1.0628. Min Range: -1.0628

Max Act: 0.7506. Min Act: -0.0000

Data Index: 1197305 (C4 (Web Text))

Max Activating Token Index: 320

Text #17

Max Range: 1.0628. Min Range: -1.0628

Max Act: 0.7974. Min Act: -0.0000

Data Index: 1251871 (C4 (Web Text))

Max Activating Token Index: 471

Text #18

Max Range: 1.0628. Min Range: -1.0628

Max Act: 0.7964. Min Act: -0.0000

Data Index: 765263 (C4 (Web Text))

Max Activating Token Index: 137

Text #19

Max Range: 1.0628. Min Range: -1.0628

Max Act: 0.7879. Min Act: -0.0000

Data Index: 363636 (C4 (Web Text))

Max Activating Token Index: 261