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

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

Neuron 2875 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1233. Min Range: -1.1233

Max Act: 1.1233. Min Act: -0.0000

Data Index: 575619 (C4 (Web Text))

Max Activating Token Index: 509

Text #1

Max Range: 1.1233. Min Range: -1.1233

Max Act: 0.9429. Min Act: -0.0000

Data Index: 981601 (C4 (Web Text))

Max Activating Token Index: 882

Text #2

Max Range: 1.1233. Min Range: -1.1233

Max Act: 0.8880. Min Act: -0.0000

Data Index: 242487 (C4 (Web Text))

Max Activating Token Index: 816

Text #3

Max Range: 1.1233. Min Range: -1.1233

Max Act: 0.8083. Min Act: -0.0000

Data Index: 931584 (C4 (Web Text))

Max Activating Token Index: 166

Text #4

Max Range: 1.1233. Min Range: -1.1233

Max Act: 0.7256. Min Act: -0.0000

Data Index: 136903 (C4 (Web Text))

Max Activating Token Index: 842

Text #5

Max Range: 1.1233. Min Range: -1.1233

Max Act: 0.6358. Min Act: -0.0000

Data Index: 597908 (C4 (Web Text))

Max Activating Token Index: 666

Text #6

Max Range: 1.1233. Min Range: -1.1233

Max Act: 0.6336. Min Act: -0.0000

Data Index: 980675 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 1.1233. Min Range: -1.1233

Max Act: 0.6261. Min Act: -0.0000

Data Index: 74616 (C4 (Web Text))

Max Activating Token Index: 789

Text #8

Max Range: 1.1233. Min Range: -1.1233

Max Act: 0.6225. Min Act: -0.0000

Data Index: 1147987 (C4 (Web Text))

Max Activating Token Index: 460

Text #9

Max Range: 1.1233. Min Range: -1.1233

Max Act: 0.6239. Min Act: -0.0000

Data Index: 1319566 (C4 (Web Text))

Max Activating Token Index: 996

Text #10

Max Range: 1.1233. Min Range: -1.1233

Max Act: 0.6237. Min Act: -0.0000

Data Index: 985414 (C4 (Web Text))

Max Activating Token Index: 796

Text #11

Max Range: 1.1233. Min Range: -1.1233

Max Act: 0.5713. Min Act: -0.0000

Data Index: 150782 (C4 (Web Text))

Max Activating Token Index: 476

Text #12

Max Range: 1.1233. Min Range: -1.1233

Max Act: 0.5238. Min Act: -0.0000

Data Index: 1207831 (C4 (Web Text))

Max Activating Token Index: 639

Text #13

Max Range: 1.1233. Min Range: -1.1233

Max Act: 0.5540. Min Act: -0.0000

Data Index: 270715 (C4 (Web Text))

Max Activating Token Index: 661

Text #14

Max Range: 1.1233. Min Range: -1.1233

Max Act: 0.5900. Min Act: -0.0000

Data Index: 654270 (C4 (Web Text))

Max Activating Token Index: 968

Text #15

Max Range: 1.1233. Min Range: -1.1233

Max Act: 0.5516. Min Act: -0.0000

Data Index: 625362 (C4 (Web Text))

Max Activating Token Index: 955

Text #16

Max Range: 1.1233. Min Range: -1.1233

Max Act: 0.5282. Min Act: -0.0000

Data Index: 199826 (C4 (Web Text))

Max Activating Token Index: 652

Text #17

Max Range: 1.1233. Min Range: -1.1233

Max Act: 0.5498. Min Act: -0.0000

Data Index: 660703 (C4 (Web Text))

Max Activating Token Index: 150

Text #18

Max Range: 1.1233. Min Range: -1.1233

Max Act: 0.5500. Min Act: -0.0000

Data Index: 855050 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 1.1233. Min Range: -1.1233

Max Act: 0.5177. Min Act: -0.0000

Data Index: 1292876 (C4 (Web Text))

Max Activating Token Index: 570