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

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

Neuron 5496 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: 2.2110. Min Range: -2.2110

Max Act: 2.2110. Min Act: -0.0000

Data Index: 162284 (C4 (Web Text))

Max Activating Token Index: 70

Text #1

Max Range: 2.2110. Min Range: -2.2110

Max Act: 2.0513. Min Act: -0.0000

Data Index: 791538 (C4 (Web Text))

Max Activating Token Index: 231

Text #2

Max Range: 2.2110. Min Range: -2.2110

Max Act: 2.1260. Min Act: -0.0000

Data Index: 1096909 (C4 (Web Text))

Max Activating Token Index: 927

Text #3

Max Range: 2.2110. Min Range: -2.2110

Max Act: 1.9532. Min Act: -0.0000

Data Index: 1508691 (Python Code)

Max Activating Token Index: 583

Text #4

Max Range: 2.2110. Min Range: -2.2110

Max Act: 1.8894. Min Act: -0.0000

Data Index: 250658 (C4 (Web Text))

Max Activating Token Index: 61

Text #5

Max Range: 2.2110. Min Range: -2.2110

Max Act: 1.8257. Min Act: -0.0000

Data Index: 1192459 (C4 (Web Text))

Max Activating Token Index: 184

Text #6

Max Range: 2.2110. Min Range: -2.2110

Max Act: 1.6678. Min Act: -0.0000

Data Index: 70216 (C4 (Web Text))

Max Activating Token Index: 628

Text #7

Max Range: 2.2110. Min Range: -2.2110

Max Act: 1.6339. Min Act: -0.0000

Data Index: 184767 (C4 (Web Text))

Max Activating Token Index: 280

Text #8

Max Range: 2.2110. Min Range: -2.2110

Max Act: 1.6131. Min Act: -0.0000

Data Index: 485857 (C4 (Web Text))

Max Activating Token Index: 594

Text #9

Max Range: 2.2110. Min Range: -2.2110

Max Act: 1.4952. Min Act: -0.0000

Data Index: 1310600 (C4 (Web Text))

Max Activating Token Index: 903

Text #10

Max Range: 2.2110. Min Range: -2.2110

Max Act: 1.5902. Min Act: -0.0000

Data Index: 1188470 (C4 (Web Text))

Max Activating Token Index: 753

Text #11

Max Range: 2.2110. Min Range: -2.2110

Max Act: 1.5727. Min Act: -0.0000

Data Index: 387986 (C4 (Web Text))

Max Activating Token Index: 962

Text #12

Max Range: 2.2110. Min Range: -2.2110

Max Act: 1.5314. Min Act: -0.0000

Data Index: 863267 (C4 (Web Text))

Max Activating Token Index: 171

Text #13

Max Range: 2.2110. Min Range: -2.2110

Max Act: 1.5278. Min Act: -0.0000

Data Index: 1199533 (C4 (Web Text))

Max Activating Token Index: 427

Text #14

Max Range: 2.2110. Min Range: -2.2110

Max Act: 1.5029. Min Act: -0.0000

Data Index: 845080 (C4 (Web Text))

Max Activating Token Index: 302

Text #15

Max Range: 2.2110. Min Range: -2.2110

Max Act: 1.4009. Min Act: -0.0000

Data Index: 1230863 (C4 (Web Text))

Max Activating Token Index: 843

Text #16

Max Range: 2.2110. Min Range: -2.2110

Max Act: 1.5245. Min Act: -0.0000

Data Index: 674831 (C4 (Web Text))

Max Activating Token Index: 858

Text #17

Max Range: 2.2110. Min Range: -2.2110

Max Act: 1.4129. Min Act: -0.0000

Data Index: 663818 (C4 (Web Text))

Max Activating Token Index: 321

Text #18

Max Range: 2.2110. Min Range: -2.2110

Max Act: 1.4097. Min Act: -0.0000

Data Index: 524468 (C4 (Web Text))

Max Activating Token Index: 387

Text #19

Max Range: 2.2110. Min Range: -2.2110

Max Act: 1.3955. Min Act: -0.0000

Data Index: 1420146 (Python Code)

Max Activating Token Index: 429