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

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

Neuron 3511 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.6138. Min Act: -0.0000

Data Index: 874176 (C4 (Web Text))

Max Activating Token Index: 425

Text #1

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.5599. Min Act: -0.0000

Data Index: 417472 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.5210. Min Act: -0.0000

Data Index: 714686 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4998. Min Act: -0.0000

Data Index: 951579 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4727. Min Act: -0.0000

Data Index: 212177 (C4 (Web Text))

Max Activating Token Index: 819

Text #5

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.3870. Min Act: -0.0000

Data Index: 825408 (C4 (Web Text))

Max Activating Token Index: 421

Text #6

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4812. Min Act: -0.0000

Data Index: 1346424 (C4 (Web Text))

Max Activating Token Index: 944

Text #7

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4366. Min Act: -0.0000

Data Index: 492774 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4021. Min Act: -0.0000

Data Index: 735084 (C4 (Web Text))

Max Activating Token Index: 406

Text #9

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.3963. Min Act: -0.0000

Data Index: 1218838 (C4 (Web Text))

Max Activating Token Index: 182

Text #10

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.3861. Min Act: -0.0000

Data Index: 532767 (C4 (Web Text))

Max Activating Token Index: 805

Text #11

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.3892. Min Act: -0.0000

Data Index: 15033 (C4 (Web Text))

Max Activating Token Index: 23

Text #12

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4002. Min Act: -0.0000

Data Index: 492612 (C4 (Web Text))

Max Activating Token Index: 639

Text #13

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4159. Min Act: -0.0000

Data Index: 1044586 (C4 (Web Text))

Max Activating Token Index: 716

Text #14

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.3799. Min Act: -0.0000

Data Index: 108840 (C4 (Web Text))

Max Activating Token Index: 477

Text #15

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.3695. Min Act: -0.0000

Data Index: 429006 (C4 (Web Text))

Max Activating Token Index: 83

Text #16

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4020. Min Act: -0.0000

Data Index: 787717 (C4 (Web Text))

Max Activating Token Index: 763

Text #17

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.3921. Min Act: -0.0000

Data Index: 1092241 (C4 (Web Text))

Max Activating Token Index: 103

Text #18

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.3593. Min Act: -0.0000

Data Index: 713204 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.3584. Min Act: -0.0000

Data Index: 771249 (C4 (Web Text))

Max Activating Token Index: 826