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

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

Neuron 5644 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9041. Min Range: -1.9041

Max Act: 1.9041. Min Act: -0.0000

Data Index: 1307587 (C4 (Web Text))

Max Activating Token Index: 320

Text #1

Max Range: 1.9041. Min Range: -1.9041

Max Act: 1.4133. Min Act: -0.0000

Data Index: 25960 (C4 (Web Text))

Max Activating Token Index: 198

Text #2

Max Range: 1.9041. Min Range: -1.9041

Max Act: 1.3860. Min Act: -0.0000

Data Index: 607558 (C4 (Web Text))

Max Activating Token Index: 935

Text #3

Max Range: 1.9041. Min Range: -1.9041

Max Act: 1.3635. Min Act: -0.0000

Data Index: 823997 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 1.9041. Min Range: -1.9041

Max Act: 1.2760. Min Act: -0.0000

Data Index: 352265 (C4 (Web Text))

Max Activating Token Index: 741

Text #5

Max Range: 1.9041. Min Range: -1.9041

Max Act: 1.2840. Min Act: -0.0000

Data Index: 391860 (C4 (Web Text))

Max Activating Token Index: 157

Text #6

Max Range: 1.9041. Min Range: -1.9041

Max Act: 1.2376. Min Act: -0.0000

Data Index: 230314 (C4 (Web Text))

Max Activating Token Index: 953

Text #7

Max Range: 1.9041. Min Range: -1.9041

Max Act: 1.2296. Min Act: -0.0000

Data Index: 1323037 (C4 (Web Text))

Max Activating Token Index: 179

Text #8

Max Range: 1.9041. Min Range: -1.9041

Max Act: 1.2207. Min Act: -0.0000

Data Index: 880653 (C4 (Web Text))

Max Activating Token Index: 763

Text #9

Max Range: 1.9041. Min Range: -1.9041

Max Act: 1.1142. Min Act: -0.0000

Data Index: 562785 (C4 (Web Text))

Max Activating Token Index: 253

Text #10

Max Range: 1.9041. Min Range: -1.9041

Max Act: 1.1826. Min Act: -0.0000

Data Index: 500239 (C4 (Web Text))

Max Activating Token Index: 1018

Text #11

Max Range: 1.9041. Min Range: -1.9041

Max Act: 1.1408. Min Act: -0.0000

Data Index: 924531 (C4 (Web Text))

Max Activating Token Index: 186

Text #12

Max Range: 1.9041. Min Range: -1.9041

Max Act: 1.1293. Min Act: -0.0000

Data Index: 1228030 (C4 (Web Text))

Max Activating Token Index: 547

Text #13

Max Range: 1.9041. Min Range: -1.9041

Max Act: 1.1312. Min Act: -0.0000

Data Index: 1148648 (C4 (Web Text))

Max Activating Token Index: 524

Text #14

Max Range: 1.9041. Min Range: -1.9041

Max Act: 1.0648. Min Act: -0.0000

Data Index: 647723 (C4 (Web Text))

Max Activating Token Index: 56

Text #15

Max Range: 1.9041. Min Range: -1.9041

Max Act: 1.0826. Min Act: -0.0000

Data Index: 304148 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 1.9041. Min Range: -1.9041

Max Act: 1.0380. Min Act: -0.0000

Data Index: 1123497 (C4 (Web Text))

Max Activating Token Index: 91

Text #17

Max Range: 1.9041. Min Range: -1.9041

Max Act: 0.9912. Min Act: -0.0000

Data Index: 454730 (C4 (Web Text))

Max Activating Token Index: 795

Text #18

Max Range: 1.9041. Min Range: -1.9041

Max Act: 0.8328. Min Act: -0.0000

Data Index: 452407 (C4 (Web Text))

Max Activating Token Index: 952

Text #19

Max Range: 1.9041. Min Range: -1.9041

Max Act: 0.8699. Min Act: -0.0000

Data Index: 803479 (C4 (Web Text))

Max Activating Token Index: 573