Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 105 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.5976. Min Act: -0.0003

Data Index: 502293 (C4 (Web Text))

Max Activating Token Index: 861

Text #1

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.6024. Min Act: -0.0003

Data Index: 889630 (C4 (Web Text))

Max Activating Token Index: 245

Text #2

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.4965. Min Act: -0.0003

Data Index: 442227 (C4 (Web Text))

Max Activating Token Index: 944

Text #3

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.5281. Min Act: -0.0003

Data Index: 93371 (C4 (Web Text))

Max Activating Token Index: 930

Text #4

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.5260. Min Act: -0.0003

Data Index: 1204145 (C4 (Web Text))

Max Activating Token Index: 313

Text #5

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.4924. Min Act: -0.0003

Data Index: 57076 (C4 (Web Text))

Max Activating Token Index: 603

Text #6

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.4983. Min Act: -0.0003

Data Index: 888128 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.4779. Min Act: -0.0003

Data Index: 1282285 (C4 (Web Text))

Max Activating Token Index: 288

Text #8

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.4737. Min Act: -0.0003

Data Index: 1137308 (C4 (Web Text))

Max Activating Token Index: 321

Text #9

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.4815. Min Act: -0.0003

Data Index: 115091 (C4 (Web Text))

Max Activating Token Index: 460

Text #10

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.4402. Min Act: -0.0003

Data Index: 732630 (C4 (Web Text))

Max Activating Token Index: 173

Text #11

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.4528. Min Act: -0.0003

Data Index: 513725 (C4 (Web Text))

Max Activating Token Index: 874

Text #12

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.4505. Min Act: -0.0003

Data Index: 1266231 (C4 (Web Text))

Max Activating Token Index: 754

Text #13

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.4844. Min Act: -0.0003

Data Index: 84223 (C4 (Web Text))

Max Activating Token Index: 628

Text #14

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.4443. Min Act: -0.0003

Data Index: 793750 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.4596. Min Act: -0.0003

Data Index: 1152824 (C4 (Web Text))

Max Activating Token Index: 727

Text #16

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.4416. Min Act: -0.0003

Data Index: 444085 (C4 (Web Text))

Max Activating Token Index: 858

Text #17

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.4437. Min Act: -0.0003

Data Index: 888471 (C4 (Web Text))

Max Activating Token Index: 734

Text #18

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.4349. Min Act: -0.0003

Data Index: 14700 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.4244. Min Act: -0.0003

Data Index: 204725 (C4 (Web Text))

Max Activating Token Index: 778