Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2112 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6928. Min Range: -0.6928

Max Act: 0.6928. Min Act: -0.0000

Data Index: 771321 (C4 (Web Text))

Max Activating Token Index: 1009

Text #1

Max Range: 0.6928. Min Range: -0.6928

Max Act: 0.6181. Min Act: -0.0000

Data Index: 499345 (C4 (Web Text))

Max Activating Token Index: 819

Text #2

Max Range: 0.6928. Min Range: -0.6928

Max Act: 0.6048. Min Act: -0.0000

Data Index: 1236924 (C4 (Web Text))

Max Activating Token Index: 801

Text #3

Max Range: 0.6928. Min Range: -0.6928

Max Act: 0.5150. Min Act: -0.0000

Data Index: 408474 (C4 (Web Text))

Max Activating Token Index: 786

Text #4

Max Range: 0.6928. Min Range: -0.6928

Max Act: 0.5168. Min Act: -0.0000

Data Index: 1166379 (C4 (Web Text))

Max Activating Token Index: 880

Text #5

Max Range: 0.6928. Min Range: -0.6928

Max Act: 0.5164. Min Act: -0.0000

Data Index: 178904 (C4 (Web Text))

Max Activating Token Index: 687

Text #6

Max Range: 0.6928. Min Range: -0.6928

Max Act: 0.4963. Min Act: -0.0000

Data Index: 1088142 (C4 (Web Text))

Max Activating Token Index: 846

Text #7

Max Range: 0.6928. Min Range: -0.6928

Max Act: 0.4722. Min Act: -0.0000

Data Index: 1290068 (C4 (Web Text))

Max Activating Token Index: 219

Text #8

Max Range: 0.6928. Min Range: -0.6928

Max Act: 0.5007. Min Act: -0.0000

Data Index: 169507 (C4 (Web Text))

Max Activating Token Index: 733

Text #9

Max Range: 0.6928. Min Range: -0.6928

Max Act: 0.4987. Min Act: -0.0000

Data Index: 596012 (C4 (Web Text))

Max Activating Token Index: 172

Text #10

Max Range: 0.6928. Min Range: -0.6928

Max Act: 0.4970. Min Act: -0.0000

Data Index: 1288051 (C4 (Web Text))

Max Activating Token Index: 335

Text #11

Max Range: 0.6928. Min Range: -0.6928

Max Act: 0.4715. Min Act: -0.0000

Data Index: 688245 (C4 (Web Text))

Max Activating Token Index: 327

Text #12

Max Range: 0.6928. Min Range: -0.6928

Max Act: 0.4638. Min Act: -0.0000

Data Index: 421591 (C4 (Web Text))

Max Activating Token Index: 788

Text #13

Max Range: 0.6928. Min Range: -0.6928

Max Act: 0.4791. Min Act: -0.0000

Data Index: 1064006 (C4 (Web Text))

Max Activating Token Index: 949

Text #14

Max Range: 0.6928. Min Range: -0.6928

Max Act: 0.4739. Min Act: -0.0000

Data Index: 804001 (C4 (Web Text))

Max Activating Token Index: 772

Text #15

Max Range: 0.6928. Min Range: -0.6928

Max Act: 0.4401. Min Act: -0.0000

Data Index: 114356 (C4 (Web Text))

Max Activating Token Index: 81

Text #16

Max Range: 0.6928. Min Range: -0.6928

Max Act: 0.4421. Min Act: -0.0000

Data Index: 783197 (C4 (Web Text))

Max Activating Token Index: 160

Text #17

Max Range: 0.6928. Min Range: -0.6928

Max Act: 0.4636. Min Act: -0.0000

Data Index: 46833 (C4 (Web Text))

Max Activating Token Index: 894

Text #18

Max Range: 0.6928. Min Range: -0.6928

Max Act: 0.4522. Min Act: -0.0000

Data Index: 38976 (C4 (Web Text))

Max Activating Token Index: 847

Text #19

Max Range: 0.6928. Min Range: -0.6928

Max Act: 0.4772. Min Act: -0.0000

Data Index: 938147 (C4 (Web Text))

Max Activating Token Index: 870