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

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

Neuron 2710 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2227. Min Range: -1.2227

Max Act: 1.2227. Min Act: -0.0000

Data Index: 347887 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 1.2227. Min Range: -1.2227

Max Act: 1.1524. Min Act: -0.0000

Data Index: 984007 (C4 (Web Text))

Max Activating Token Index: 295

Text #2

Max Range: 1.2227. Min Range: -1.2227

Max Act: 1.1181. Min Act: -0.0000

Data Index: 997072 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 1.2227. Min Range: -1.2227

Max Act: 0.8238. Min Act: -0.0000

Data Index: 123386 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 1.2227. Min Range: -1.2227

Max Act: 0.7389. Min Act: -0.0000

Data Index: 1316285 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 1.2227. Min Range: -1.2227

Max Act: 0.7988. Min Act: -0.0000

Data Index: 763675 (C4 (Web Text))

Max Activating Token Index: 40

Text #6

Max Range: 1.2227. Min Range: -1.2227

Max Act: 0.7476. Min Act: -0.0000

Data Index: 1352102 (C4 (Web Text))

Max Activating Token Index: 422

Text #7

Max Range: 1.2227. Min Range: -1.2227

Max Act: 0.7493. Min Act: -0.0000

Data Index: 509733 (C4 (Web Text))

Max Activating Token Index: 498

Text #8

Max Range: 1.2227. Min Range: -1.2227

Max Act: 0.7159. Min Act: -0.0000

Data Index: 792430 (C4 (Web Text))

Max Activating Token Index: 991

Text #9

Max Range: 1.2227. Min Range: -1.2227

Max Act: 0.7629. Min Act: -0.0000

Data Index: 867913 (C4 (Web Text))

Max Activating Token Index: 840

Text #10

Max Range: 1.2227. Min Range: -1.2227

Max Act: 0.7215. Min Act: -0.0000

Data Index: 189883 (C4 (Web Text))

Max Activating Token Index: 559

Text #11

Max Range: 1.2227. Min Range: -1.2227

Max Act: 0.6914. Min Act: -0.0000

Data Index: 320752 (C4 (Web Text))

Max Activating Token Index: 47

Text #12

Max Range: 1.2227. Min Range: -1.2227

Max Act: 0.7090. Min Act: -0.0000

Data Index: 328796 (C4 (Web Text))

Max Activating Token Index: 434

Text #13

Max Range: 1.2227. Min Range: -1.2227

Max Act: 0.6949. Min Act: -0.0000

Data Index: 11890 (C4 (Web Text))

Max Activating Token Index: 942

Text #14

Max Range: 1.2227. Min Range: -1.2227

Max Act: 0.6989. Min Act: -0.0000

Data Index: 319313 (C4 (Web Text))

Max Activating Token Index: 919

Text #15

Max Range: 1.2227. Min Range: -1.2227

Max Act: 0.6886. Min Act: -0.0000

Data Index: 522807 (C4 (Web Text))

Max Activating Token Index: 524

Text #16

Max Range: 1.2227. Min Range: -1.2227

Max Act: 0.6646. Min Act: -0.0000

Data Index: 273636 (C4 (Web Text))

Max Activating Token Index: 982

Text #17

Max Range: 1.2227. Min Range: -1.2227

Max Act: 0.6792. Min Act: -0.0000

Data Index: 830798 (C4 (Web Text))

Max Activating Token Index: 326

Text #18

Max Range: 1.2227. Min Range: -1.2227

Max Act: 0.6782. Min Act: -0.0000

Data Index: 192433 (C4 (Web Text))

Max Activating Token Index: 758

Text #19

Max Range: 1.2227. Min Range: -1.2227

Max Act: 0.6799. Min Act: -0.0000

Data Index: 1316774 (C4 (Web Text))

Max Activating Token Index: 833