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

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

Neuron 1422 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6794. Min Range: -0.6794

Max Act: 0.6794. Min Act: -0.0000

Data Index: 272546 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 0.6794. Min Range: -0.6794

Max Act: 0.6702. Min Act: -0.0000

Data Index: 651845 (C4 (Web Text))

Max Activating Token Index: 266

Text #2

Max Range: 0.6794. Min Range: -0.6794

Max Act: 0.5644. Min Act: -0.0000

Data Index: 320287 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 0.6794. Min Range: -0.6794

Max Act: 0.5536. Min Act: -0.0000

Data Index: 372584 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 0.6794. Min Range: -0.6794

Max Act: 0.5367. Min Act: -0.0001

Data Index: 1032535 (C4 (Web Text))

Max Activating Token Index: 486

Text #5

Max Range: 0.6794. Min Range: -0.6794

Max Act: 0.5713. Min Act: -0.0000

Data Index: 535228 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.6794. Min Range: -0.6794

Max Act: 0.5085. Min Act: -0.0000

Data Index: 1257923 (C4 (Web Text))

Max Activating Token Index: 104

Text #7

Max Range: 0.6794. Min Range: -0.6794

Max Act: 0.5227. Min Act: -0.0000

Data Index: 301045 (C4 (Web Text))

Max Activating Token Index: 458

Text #8

Max Range: 0.6794. Min Range: -0.6794

Max Act: 0.5189. Min Act: -0.0001

Data Index: 497241 (C4 (Web Text))

Max Activating Token Index: 192

Text #9

Max Range: 0.6794. Min Range: -0.6794

Max Act: 0.5188. Min Act: -0.0000

Data Index: 647484 (C4 (Web Text))

Max Activating Token Index: 162

Text #10

Max Range: 0.6794. Min Range: -0.6794

Max Act: 0.5157. Min Act: -0.0001

Data Index: 240456 (C4 (Web Text))

Max Activating Token Index: 883

Text #11

Max Range: 0.6794. Min Range: -0.6794

Max Act: 0.4803. Min Act: -0.0001

Data Index: 1186290 (C4 (Web Text))

Max Activating Token Index: 785

Text #12

Max Range: 0.6794. Min Range: -0.6794

Max Act: 0.5099. Min Act: -0.0000

Data Index: 310258 (C4 (Web Text))

Max Activating Token Index: 567

Text #13

Max Range: 0.6794. Min Range: -0.6794

Max Act: 0.5073. Min Act: -0.0000

Data Index: 824129 (C4 (Web Text))

Max Activating Token Index: 815

Text #14

Max Range: 0.6794. Min Range: -0.6794

Max Act: 0.5025. Min Act: -0.0000

Data Index: 579603 (C4 (Web Text))

Max Activating Token Index: 846

Text #15

Max Range: 0.6794. Min Range: -0.6794

Max Act: 0.4863. Min Act: -0.0001

Data Index: 1132509 (C4 (Web Text))

Max Activating Token Index: 934

Text #16

Max Range: 0.6794. Min Range: -0.6794

Max Act: 0.4852. Min Act: -0.0000

Data Index: 400367 (C4 (Web Text))

Max Activating Token Index: 686

Text #17

Max Range: 0.6794. Min Range: -0.6794

Max Act: 0.4819. Min Act: -0.0000

Data Index: 1103706 (C4 (Web Text))

Max Activating Token Index: 34

Text #18

Max Range: 0.6794. Min Range: -0.6794

Max Act: 0.4970. Min Act: -0.0000

Data Index: 65692 (C4 (Web Text))

Max Activating Token Index: 961

Text #19

Max Range: 0.6794. Min Range: -0.6794

Max Act: 0.4772. Min Act: -0.0001

Data Index: 633256 (C4 (Web Text))

Max Activating Token Index: 542