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

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

Neuron 4921 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0186. Min Range: -2.0186

Max Act: 1.9640. Min Act: -0.0000

Data Index: 326515 (C4 (Web Text))

Max Activating Token Index: 826

Text #1

Max Range: 2.0186. Min Range: -2.0186

Max Act: 1.8260. Min Act: -0.0000

Data Index: 933856 (C4 (Web Text))

Max Activating Token Index: 700

Text #2

Max Range: 2.0186. Min Range: -2.0186

Max Act: 1.9116. Min Act: -0.0000

Data Index: 504345 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 2.0186. Min Range: -2.0186

Max Act: 1.8162. Min Act: -0.0000

Data Index: 304042 (C4 (Web Text))

Max Activating Token Index: 948

Text #4

Max Range: 2.0186. Min Range: -2.0186

Max Act: 1.7771. Min Act: -0.0000

Data Index: 1250290 (C4 (Web Text))

Max Activating Token Index: 355

Text #5

Max Range: 2.0186. Min Range: -2.0186

Max Act: 2.0053. Min Act: -0.0000

Data Index: 1235707 (C4 (Web Text))

Max Activating Token Index: 717

Text #6

Max Range: 2.0186. Min Range: -2.0186

Max Act: 1.7806. Min Act: -0.0000

Data Index: 614907 (C4 (Web Text))

Max Activating Token Index: 258

Text #7

Max Range: 2.0186. Min Range: -2.0186

Max Act: 1.3323. Min Act: -0.0000

Data Index: 103964 (C4 (Web Text))

Max Activating Token Index: 976

Text #8

Max Range: 2.0186. Min Range: -2.0186

Max Act: 1.8631. Min Act: -0.0000

Data Index: 81042 (C4 (Web Text))

Max Activating Token Index: 962

Text #9

Max Range: 2.0186. Min Range: -2.0186

Max Act: 1.7602. Min Act: -0.0000

Data Index: 1330419 (C4 (Web Text))

Max Activating Token Index: 845

Text #10

Max Range: 2.0186. Min Range: -2.0186

Max Act: 1.7113. Min Act: -0.0000

Data Index: 976494 (C4 (Web Text))

Max Activating Token Index: 771

Text #11

Max Range: 2.0186. Min Range: -2.0186

Max Act: 2.0186. Min Act: -0.0000

Data Index: 519633 (C4 (Web Text))

Max Activating Token Index: 936

Text #12

Max Range: 2.0186. Min Range: -2.0186

Max Act: 1.5847. Min Act: -0.0000

Data Index: 723755 (C4 (Web Text))

Max Activating Token Index: 739

Text #13

Max Range: 2.0186. Min Range: -2.0186

Max Act: 1.6417. Min Act: -0.0000

Data Index: 767307 (C4 (Web Text))

Max Activating Token Index: 591

Text #14

Max Range: 2.0186. Min Range: -2.0186

Max Act: 1.5249. Min Act: -0.0000

Data Index: 1152531 (C4 (Web Text))

Max Activating Token Index: 92

Text #15

Max Range: 2.0186. Min Range: -2.0186

Max Act: 1.8124. Min Act: -0.0000

Data Index: 612961 (C4 (Web Text))

Max Activating Token Index: 349

Text #16

Max Range: 2.0186. Min Range: -2.0186

Max Act: 1.7045. Min Act: -0.0000

Data Index: 1065550 (C4 (Web Text))

Max Activating Token Index: 995

Text #17

Max Range: 2.0186. Min Range: -2.0186

Max Act: 1.5875. Min Act: -0.0000

Data Index: 264447 (C4 (Web Text))

Max Activating Token Index: 962

Text #18

Max Range: 2.0186. Min Range: -2.0186

Max Act: 1.4804. Min Act: -0.0000

Data Index: 131845 (C4 (Web Text))

Max Activating Token Index: 790

Text #19

Max Range: 2.0186. Min Range: -2.0186

Max Act: 1.7192. Min Act: -0.0000

Data Index: 561456 (C4 (Web Text))

Max Activating Token Index: 248