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

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

Neuron 3982 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.6965. Min Act: -0.0001

Data Index: 729881 (C4 (Web Text))

Max Activating Token Index: 651

Text #1

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.6223. Min Act: -0.0000

Data Index: 521188 (C4 (Web Text))

Max Activating Token Index: 483

Text #2

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.5562. Min Act: -0.0001

Data Index: 410626 (C4 (Web Text))

Max Activating Token Index: 605

Text #3

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.5851. Min Act: -0.0000

Data Index: 1145186 (C4 (Web Text))

Max Activating Token Index: 801

Text #4

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.5236. Min Act: -0.0001

Data Index: 865041 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.5501. Min Act: -0.0000

Data Index: 497061 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.5319. Min Act: -0.0001

Data Index: 1201575 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.5256. Min Act: -0.0001

Data Index: 206881 (C4 (Web Text))

Max Activating Token Index: 386

Text #8

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.5245. Min Act: -0.0000

Data Index: 960961 (C4 (Web Text))

Max Activating Token Index: 768

Text #9

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.5112. Min Act: -0.0000

Data Index: 1017743 (C4 (Web Text))

Max Activating Token Index: 753

Text #10

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.5030. Min Act: -0.0000

Data Index: 523610 (C4 (Web Text))

Max Activating Token Index: 793

Text #11

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.5012. Min Act: -0.0000

Data Index: 928816 (C4 (Web Text))

Max Activating Token Index: 62

Text #12

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.5049. Min Act: -0.0000

Data Index: 380776 (C4 (Web Text))

Max Activating Token Index: 917

Text #13

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.5011. Min Act: -0.0001

Data Index: 290009 (C4 (Web Text))

Max Activating Token Index: 876

Text #14

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.4991. Min Act: -0.0000

Data Index: 610116 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.4857. Min Act: -0.0000

Data Index: 707916 (C4 (Web Text))

Max Activating Token Index: 271

Text #16

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.4955. Min Act: -0.0000

Data Index: 636848 (C4 (Web Text))

Max Activating Token Index: 294

Text #17

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.4954. Min Act: -0.0000

Data Index: 69450 (C4 (Web Text))

Max Activating Token Index: 919

Text #18

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.4898. Min Act: -0.0000

Data Index: 393094 (C4 (Web Text))

Max Activating Token Index: 455

Text #19

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.4865. Min Act: -0.0001

Data Index: 789144 (C4 (Web Text))

Max Activating Token Index: 777