Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 122 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0044. Min Act: -0.0003

Data Index: 631707 (C4 (Web Text))

Max Activating Token Index: 260

Text #1

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0038. Min Act: -0.0003

Data Index: 1341801 (C4 (Web Text))

Max Activating Token Index: 195

Text #2

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0035. Min Act: -0.0002

Data Index: 1639453 (Python Code)

Max Activating Token Index: 601

Text #3

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0033. Min Act: -0.0003

Data Index: 935635 (C4 (Web Text))

Max Activating Token Index: 768

Text #4

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0031. Min Act: -0.0003

Data Index: 12346 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0033. Min Act: -0.0003

Data Index: 279583 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0033. Min Act: -0.0003

Data Index: 1012786 (C4 (Web Text))

Max Activating Token Index: 455

Text #7

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0031. Min Act: -0.0002

Data Index: 1321525 (C4 (Web Text))

Max Activating Token Index: 69

Text #8

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0031. Min Act: -0.0003

Data Index: 613508 (C4 (Web Text))

Max Activating Token Index: 326

Text #9

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0029. Min Act: -0.0003

Data Index: 1352978 (C4 (Web Text))

Max Activating Token Index: 470

Text #10

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0030. Min Act: -0.0003

Data Index: 771050 (C4 (Web Text))

Max Activating Token Index: 671

Text #11

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0027. Min Act: -0.0003

Data Index: 423398 (C4 (Web Text))

Max Activating Token Index: 53

Text #12

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0029. Min Act: -0.0003

Data Index: 651153 (C4 (Web Text))

Max Activating Token Index: 563

Text #13

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0029. Min Act: -0.0002

Data Index: 1477308 (Python Code)

Max Activating Token Index: 679

Text #14

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0027. Min Act: -0.0003

Data Index: 658555 (C4 (Web Text))

Max Activating Token Index: 350

Text #15

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0026. Min Act: -0.0003

Data Index: 1123739 (C4 (Web Text))

Max Activating Token Index: 819

Text #16

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0025. Min Act: -0.0003

Data Index: 676789 (C4 (Web Text))

Max Activating Token Index: 147

Text #17

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0025. Min Act: -0.0002

Data Index: 467133 (C4 (Web Text))

Max Activating Token Index: 205

Text #18

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0025. Min Act: -0.0003

Data Index: 599389 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0025. Min Act: -0.0003

Data Index: 933977 (C4 (Web Text))

Max Activating Token Index: 233