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

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

Neuron 1503 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9544. Min Range: -1.9544

Max Act: 1.7884. Min Act: -0.0001

Data Index: 845721 (C4 (Web Text))

Max Activating Token Index: 563

Text #1

Max Range: 1.9544. Min Range: -1.9544

Max Act: 1.9544. Min Act: -0.0001

Data Index: 4381 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 1.9544. Min Range: -1.9544

Max Act: 1.7709. Min Act: -0.0001

Data Index: 588859 (C4 (Web Text))

Max Activating Token Index: 112

Text #3

Max Range: 1.9544. Min Range: -1.9544

Max Act: 1.6853. Min Act: -0.0001

Data Index: 991809 (C4 (Web Text))

Max Activating Token Index: 661

Text #4

Max Range: 1.9544. Min Range: -1.9544

Max Act: 1.8111. Min Act: -0.0001

Data Index: 252162 (C4 (Web Text))

Max Activating Token Index: 24

Text #5

Max Range: 1.9544. Min Range: -1.9544

Max Act: 1.7701. Min Act: -0.0001

Data Index: 613999 (C4 (Web Text))

Max Activating Token Index: 329

Text #6

Max Range: 1.9544. Min Range: -1.9544

Max Act: 1.7264. Min Act: -0.0001

Data Index: 5443 (C4 (Web Text))

Max Activating Token Index: 338

Text #7

Max Range: 1.9544. Min Range: -1.9544

Max Act: 1.6788. Min Act: -0.0001

Data Index: 1016461 (C4 (Web Text))

Max Activating Token Index: 252

Text #8

Max Range: 1.9544. Min Range: -1.9544

Max Act: 1.7451. Min Act: -0.0001

Data Index: 1291582 (C4 (Web Text))

Max Activating Token Index: 100

Text #9

Max Range: 1.9544. Min Range: -1.9544

Max Act: 1.6755. Min Act: -0.0001

Data Index: 28069 (C4 (Web Text))

Max Activating Token Index: 66

Text #10

Max Range: 1.9544. Min Range: -1.9544

Max Act: 1.6424. Min Act: -0.0001

Data Index: 1247064 (C4 (Web Text))

Max Activating Token Index: 84

Text #11

Max Range: 1.9544. Min Range: -1.9544

Max Act: 1.5747. Min Act: -0.0001

Data Index: 1101549 (C4 (Web Text))

Max Activating Token Index: 369

Text #12

Max Range: 1.9544. Min Range: -1.9544

Max Act: 1.6011. Min Act: -0.0001

Data Index: 699396 (C4 (Web Text))

Max Activating Token Index: 842

Text #13

Max Range: 1.9544. Min Range: -1.9544

Max Act: 1.6022. Min Act: -0.0001

Data Index: 123460 (C4 (Web Text))

Max Activating Token Index: 950

Text #14

Max Range: 1.9544. Min Range: -1.9544

Max Act: 1.5416. Min Act: -0.0001

Data Index: 1328809 (C4 (Web Text))

Max Activating Token Index: 4

Text #15

Max Range: 1.9544. Min Range: -1.9544

Max Act: 1.5177. Min Act: -0.0001

Data Index: 764362 (C4 (Web Text))

Max Activating Token Index: 777

Text #16

Max Range: 1.9544. Min Range: -1.9544

Max Act: 1.5928. Min Act: -0.0001

Data Index: 1054093 (C4 (Web Text))

Max Activating Token Index: 49

Text #17

Max Range: 1.9544. Min Range: -1.9544

Max Act: 1.5008. Min Act: -0.0001

Data Index: 239782 (C4 (Web Text))

Max Activating Token Index: 716

Text #18

Max Range: 1.9544. Min Range: -1.9544

Max Act: 1.5755. Min Act: -0.0001

Data Index: 16309 (C4 (Web Text))

Max Activating Token Index: 649

Text #19

Max Range: 1.9544. Min Range: -1.9544

Max Act: 1.4858. Min Act: -0.0001

Data Index: 338715 (C4 (Web Text))

Max Activating Token Index: 19