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

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

Neuron 3695 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5882. Min Range: -1.5882

Max Act: 1.5882. Min Act: -0.0002

Data Index: 11386 (C4 (Web Text))

Max Activating Token Index: 990

Text #1

Max Range: 1.5882. Min Range: -1.5882

Max Act: 1.5801. Min Act: -0.0002

Data Index: 668857 (C4 (Web Text))

Max Activating Token Index: 705

Text #2

Max Range: 1.5882. Min Range: -1.5882

Max Act: 1.5594. Min Act: -0.0002

Data Index: 707363 (C4 (Web Text))

Max Activating Token Index: 954

Text #3

Max Range: 1.5882. Min Range: -1.5882

Max Act: 1.5409. Min Act: -0.0002

Data Index: 514954 (C4 (Web Text))

Max Activating Token Index: 80

Text #4

Max Range: 1.5882. Min Range: -1.5882

Max Act: 1.5468. Min Act: -0.0002

Data Index: 735331 (C4 (Web Text))

Max Activating Token Index: 962

Text #5

Max Range: 1.5882. Min Range: -1.5882

Max Act: 1.4171. Min Act: -0.0002

Data Index: 1028766 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 1.5882. Min Range: -1.5882

Max Act: 1.5710. Min Act: -0.0002

Data Index: 96912 (C4 (Web Text))

Max Activating Token Index: 699

Text #7

Max Range: 1.5882. Min Range: -1.5882

Max Act: 1.4846. Min Act: -0.0002

Data Index: 560359 (C4 (Web Text))

Max Activating Token Index: 687

Text #8

Max Range: 1.5882. Min Range: -1.5882

Max Act: 1.4527. Min Act: -0.0002

Data Index: 917200 (C4 (Web Text))

Max Activating Token Index: 788

Text #9

Max Range: 1.5882. Min Range: -1.5882

Max Act: 1.5355. Min Act: -0.0002

Data Index: 1321696 (C4 (Web Text))

Max Activating Token Index: 650

Text #10

Max Range: 1.5882. Min Range: -1.5882

Max Act: 1.5063. Min Act: -0.0002

Data Index: 1147737 (C4 (Web Text))

Max Activating Token Index: 833

Text #11

Max Range: 1.5882. Min Range: -1.5882

Max Act: 1.5088. Min Act: -0.0002

Data Index: 834532 (C4 (Web Text))

Max Activating Token Index: 596

Text #12

Max Range: 1.5882. Min Range: -1.5882

Max Act: 1.4780. Min Act: -0.0002

Data Index: 1114217 (C4 (Web Text))

Max Activating Token Index: 269

Text #13

Max Range: 1.5882. Min Range: -1.5882

Max Act: 1.5176. Min Act: -0.0001

Data Index: 13724 (C4 (Web Text))

Max Activating Token Index: 55

Text #14

Max Range: 1.5882. Min Range: -1.5882

Max Act: 1.5007. Min Act: -0.0002

Data Index: 1076853 (C4 (Web Text))

Max Activating Token Index: 986

Text #15

Max Range: 1.5882. Min Range: -1.5882

Max Act: 1.4558. Min Act: -0.0002

Data Index: 704567 (C4 (Web Text))

Max Activating Token Index: 106

Text #16

Max Range: 1.5882. Min Range: -1.5882

Max Act: 1.5217. Min Act: -0.0002

Data Index: 182191 (C4 (Web Text))

Max Activating Token Index: 130

Text #17

Max Range: 1.5882. Min Range: -1.5882

Max Act: 1.4798. Min Act: -0.0002

Data Index: 1256840 (C4 (Web Text))

Max Activating Token Index: 1013

Text #18

Max Range: 1.5882. Min Range: -1.5882

Max Act: 1.4061. Min Act: -0.0002

Data Index: 628579 (C4 (Web Text))

Max Activating Token Index: 946

Text #19

Max Range: 1.5882. Min Range: -1.5882

Max Act: 1.4689. Min Act: -0.0002

Data Index: 1350309 (C4 (Web Text))

Max Activating Token Index: 984