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

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

Neuron 1881 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2936. Min Range: -1.2936

Max Act: 1.2936. Min Act: -0.0001

Data Index: 424334 (C4 (Web Text))

Max Activating Token Index: 1001

Text #1

Max Range: 1.2936. Min Range: -1.2936

Max Act: 1.2168. Min Act: -0.0001

Data Index: 216924 (C4 (Web Text))

Max Activating Token Index: 202

Text #2

Max Range: 1.2936. Min Range: -1.2936

Max Act: 1.0736. Min Act: -0.0001

Data Index: 625621 (C4 (Web Text))

Max Activating Token Index: 1013

Text #3

Max Range: 1.2936. Min Range: -1.2936

Max Act: 1.0995. Min Act: -0.0001

Data Index: 77545 (C4 (Web Text))

Max Activating Token Index: 890

Text #4

Max Range: 1.2936. Min Range: -1.2936

Max Act: 1.1137. Min Act: -0.0001

Data Index: 209199 (C4 (Web Text))

Max Activating Token Index: 807

Text #5

Max Range: 1.2936. Min Range: -1.2936

Max Act: 1.0726. Min Act: -0.0001

Data Index: 955173 (C4 (Web Text))

Max Activating Token Index: 899

Text #6

Max Range: 1.2936. Min Range: -1.2936

Max Act: 1.0462. Min Act: -0.0001

Data Index: 998769 (C4 (Web Text))

Max Activating Token Index: 972

Text #7

Max Range: 1.2936. Min Range: -1.2936

Max Act: 1.0761. Min Act: -0.0001

Data Index: 377316 (C4 (Web Text))

Max Activating Token Index: 590

Text #8

Max Range: 1.2936. Min Range: -1.2936

Max Act: 1.0861. Min Act: -0.0001

Data Index: 1169532 (C4 (Web Text))

Max Activating Token Index: 452

Text #9

Max Range: 1.2936. Min Range: -1.2936

Max Act: 1.0474. Min Act: -0.0001

Data Index: 127060 (C4 (Web Text))

Max Activating Token Index: 408

Text #10

Max Range: 1.2936. Min Range: -1.2936

Max Act: 1.0724. Min Act: -0.0001

Data Index: 1199300 (C4 (Web Text))

Max Activating Token Index: 544

Text #11

Max Range: 1.2936. Min Range: -1.2936

Max Act: 0.9966. Min Act: -0.0001

Data Index: 930155 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 1.2936. Min Range: -1.2936

Max Act: 1.0492. Min Act: -0.0001

Data Index: 374571 (C4 (Web Text))

Max Activating Token Index: 556

Text #13

Max Range: 1.2936. Min Range: -1.2936

Max Act: 1.0158. Min Act: -0.0001

Data Index: 379060 (C4 (Web Text))

Max Activating Token Index: 167

Text #14

Max Range: 1.2936. Min Range: -1.2936

Max Act: 1.0151. Min Act: -0.0001

Data Index: 765736 (C4 (Web Text))

Max Activating Token Index: 347

Text #15

Max Range: 1.2936. Min Range: -1.2936

Max Act: 1.0168. Min Act: -0.0001

Data Index: 1151187 (C4 (Web Text))

Max Activating Token Index: 556

Text #16

Max Range: 1.2936. Min Range: -1.2936

Max Act: 0.9803. Min Act: -0.0001

Data Index: 1087482 (C4 (Web Text))

Max Activating Token Index: 250

Text #17

Max Range: 1.2936. Min Range: -1.2936

Max Act: 0.9797. Min Act: -0.0001

Data Index: 1042887 (C4 (Web Text))

Max Activating Token Index: 599

Text #18

Max Range: 1.2936. Min Range: -1.2936

Max Act: 1.0323. Min Act: -0.0001

Data Index: 603317 (C4 (Web Text))

Max Activating Token Index: 72

Text #19

Max Range: 1.2936. Min Range: -1.2936

Max Act: 1.0012. Min Act: -0.0001

Data Index: 842223 (C4 (Web Text))

Max Activating Token Index: 115