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

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

Neuron 2505 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3267. Min Range: -1.3267

Max Act: 1.3267. Min Act: -0.0002

Data Index: 331602 (C4 (Web Text))

Max Activating Token Index: 210

Text #1

Max Range: 1.3267. Min Range: -1.3267

Max Act: 1.3184. Min Act: -0.0002

Data Index: 1173957 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 1.3267. Min Range: -1.3267

Max Act: 1.2878. Min Act: -0.0002

Data Index: 980687 (C4 (Web Text))

Max Activating Token Index: 734

Text #3

Max Range: 1.3267. Min Range: -1.3267

Max Act: 1.2817. Min Act: -0.0002

Data Index: 316511 (C4 (Web Text))

Max Activating Token Index: 582

Text #4

Max Range: 1.3267. Min Range: -1.3267

Max Act: 1.3160. Min Act: -0.0002

Data Index: 1096042 (C4 (Web Text))

Max Activating Token Index: 668

Text #5

Max Range: 1.3267. Min Range: -1.3267

Max Act: 1.2583. Min Act: -0.0002

Data Index: 1292126 (C4 (Web Text))

Max Activating Token Index: 563

Text #6

Max Range: 1.3267. Min Range: -1.3267

Max Act: 1.1875. Min Act: -0.0002

Data Index: 441915 (C4 (Web Text))

Max Activating Token Index: 414

Text #7

Max Range: 1.3267. Min Range: -1.3267

Max Act: 1.1973. Min Act: -0.0002

Data Index: 718726 (C4 (Web Text))

Max Activating Token Index: 379

Text #8

Max Range: 1.3267. Min Range: -1.3267

Max Act: 1.1039. Min Act: -0.0002

Data Index: 1052728 (C4 (Web Text))

Max Activating Token Index: 805

Text #9

Max Range: 1.3267. Min Range: -1.3267

Max Act: 1.1234. Min Act: -0.0002

Data Index: 1201941 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 1.3267. Min Range: -1.3267

Max Act: 1.0795. Min Act: -0.0002

Data Index: 1257490 (C4 (Web Text))

Max Activating Token Index: 654

Text #11

Max Range: 1.3267. Min Range: -1.3267

Max Act: 1.1031. Min Act: -0.0002

Data Index: 1330561 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 1.3267. Min Range: -1.3267

Max Act: 1.0971. Min Act: -0.0002

Data Index: 404041 (C4 (Web Text))

Max Activating Token Index: 127

Text #13

Max Range: 1.3267. Min Range: -1.3267

Max Act: 1.0973. Min Act: -0.0002

Data Index: 1188964 (C4 (Web Text))

Max Activating Token Index: 307

Text #14

Max Range: 1.3267. Min Range: -1.3267

Max Act: 1.0924. Min Act: -0.0002

Data Index: 906554 (C4 (Web Text))

Max Activating Token Index: 482

Text #15

Max Range: 1.3267. Min Range: -1.3267

Max Act: 1.1176. Min Act: -0.0002

Data Index: 778754 (C4 (Web Text))

Max Activating Token Index: 878

Text #16

Max Range: 1.3267. Min Range: -1.3267

Max Act: 1.0508. Min Act: -0.0002

Data Index: 485223 (C4 (Web Text))

Max Activating Token Index: 726

Text #17

Max Range: 1.3267. Min Range: -1.3267

Max Act: 1.0771. Min Act: -0.0002

Data Index: 352105 (C4 (Web Text))

Max Activating Token Index: 591

Text #18

Max Range: 1.3267. Min Range: -1.3267

Max Act: 1.0730. Min Act: -0.0002

Data Index: 1109285 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 1.3267. Min Range: -1.3267

Max Act: 1.0662. Min Act: -0.0002

Data Index: 892385 (C4 (Web Text))

Max Activating Token Index: 346