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

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

Neuron 3047 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: 1.3430. Min Range: -1.3430

Max Act: 1.3430. Min Act: -0.0000

Data Index: 352316 (C4 (Web Text))

Max Activating Token Index: 504

Text #1

Max Range: 1.3430. Min Range: -1.3430

Max Act: 1.2134. Min Act: -0.0000

Data Index: 1354209 (C4 (Web Text))

Max Activating Token Index: 130

Text #2

Max Range: 1.3430. Min Range: -1.3430

Max Act: 1.1071. Min Act: -0.0000

Data Index: 14824 (C4 (Web Text))

Max Activating Token Index: 281

Text #3

Max Range: 1.3430. Min Range: -1.3430

Max Act: 1.0187. Min Act: -0.0000

Data Index: 922328 (C4 (Web Text))

Max Activating Token Index: 759

Text #4

Max Range: 1.3430. Min Range: -1.3430

Max Act: 0.9938. Min Act: -0.0000

Data Index: 186910 (C4 (Web Text))

Max Activating Token Index: 316

Text #5

Max Range: 1.3430. Min Range: -1.3430

Max Act: 1.0279. Min Act: -0.0000

Data Index: 1039265 (C4 (Web Text))

Max Activating Token Index: 296

Text #6

Max Range: 1.3430. Min Range: -1.3430

Max Act: 1.0390. Min Act: -0.0000

Data Index: 436594 (C4 (Web Text))

Max Activating Token Index: 917

Text #7

Max Range: 1.3430. Min Range: -1.3430

Max Act: 1.0692. Min Act: -0.0000

Data Index: 250675 (C4 (Web Text))

Max Activating Token Index: 724

Text #8

Max Range: 1.3430. Min Range: -1.3430

Max Act: 0.9978. Min Act: -0.0000

Data Index: 678959 (C4 (Web Text))

Max Activating Token Index: 191

Text #9

Max Range: 1.3430. Min Range: -1.3430

Max Act: 0.9573. Min Act: -0.0000

Data Index: 291816 (C4 (Web Text))

Max Activating Token Index: 215

Text #10

Max Range: 1.3430. Min Range: -1.3430

Max Act: 0.9698. Min Act: -0.0000

Data Index: 120799 (C4 (Web Text))

Max Activating Token Index: 158

Text #11

Max Range: 1.3430. Min Range: -1.3430

Max Act: 0.9632. Min Act: -0.0000

Data Index: 206299 (C4 (Web Text))

Max Activating Token Index: 682

Text #12

Max Range: 1.3430. Min Range: -1.3430

Max Act: 0.9603. Min Act: -0.0000

Data Index: 1550230 (Python Code)

Max Activating Token Index: 954

Text #13

Max Range: 1.3430. Min Range: -1.3430

Max Act: 0.9507. Min Act: -0.0000

Data Index: 676864 (C4 (Web Text))

Max Activating Token Index: 108

Text #14

Max Range: 1.3430. Min Range: -1.3430

Max Act: 0.8842. Min Act: -0.0000

Data Index: 1032254 (C4 (Web Text))

Max Activating Token Index: 518

Text #15

Max Range: 1.3430. Min Range: -1.3430

Max Act: 0.9377. Min Act: -0.0000

Data Index: 916227 (C4 (Web Text))

Max Activating Token Index: 518

Text #16

Max Range: 1.3430. Min Range: -1.3430

Max Act: 0.9357. Min Act: -0.0000

Data Index: 172163 (C4 (Web Text))

Max Activating Token Index: 425

Text #17

Max Range: 1.3430. Min Range: -1.3430

Max Act: 0.9794. Min Act: -0.0000

Data Index: 1094684 (C4 (Web Text))

Max Activating Token Index: 370

Text #18

Max Range: 1.3430. Min Range: -1.3430

Max Act: 0.9212. Min Act: -0.0000

Data Index: 1280708 (C4 (Web Text))

Max Activating Token Index: 837

Text #19

Max Range: 1.3430. Min Range: -1.3430

Max Act: 0.8841. Min Act: -0.0000

Data Index: 578399 (C4 (Web Text))

Max Activating Token Index: 121