Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1989 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.6283. Min Range: -5.6283

Max Act: 5.6283. Min Act: -0.1700

Data Index: 34292 (C4 (Web Text))

Max Activating Token Index: 991

Text #1

Max Range: 5.6283. Min Range: -5.6283

Max Act: 5.3470. Min Act: -0.1700

Data Index: 1135748 (C4 (Web Text))

Max Activating Token Index: 939

Text #2

Max Range: 5.6283. Min Range: -5.6283

Max Act: 5.2845. Min Act: -0.1700

Data Index: 1039039 (C4 (Web Text))

Max Activating Token Index: 427

Text #3

Max Range: 5.6283. Min Range: -5.6283

Max Act: 5.3470. Min Act: -0.1700

Data Index: 600809 (C4 (Web Text))

Max Activating Token Index: 752

Text #4

Max Range: 5.6283. Min Range: -5.6283

Max Act: 5.3783. Min Act: -0.1700

Data Index: 33911 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 5.6283. Min Range: -5.6283

Max Act: 5.3158. Min Act: -0.1700

Data Index: 1303094 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 5.6283. Min Range: -5.6283

Max Act: 5.2845. Min Act: -0.1700

Data Index: 637338 (C4 (Web Text))

Max Activating Token Index: 630

Text #7

Max Range: 5.6283. Min Range: -5.6283

Max Act: 5.2220. Min Act: -0.1700

Data Index: 688230 (C4 (Web Text))

Max Activating Token Index: 506

Text #8

Max Range: 5.6283. Min Range: -5.6283

Max Act: 5.1908. Min Act: -0.1700

Data Index: 347657 (C4 (Web Text))

Max Activating Token Index: 836

Text #9

Max Range: 5.6283. Min Range: -5.6283

Max Act: 5.1908. Min Act: -0.1700

Data Index: 290862 (C4 (Web Text))

Max Activating Token Index: 223

Text #10

Max Range: 5.6283. Min Range: -5.6283

Max Act: 5.1908. Min Act: -0.1700

Data Index: 208081 (C4 (Web Text))

Max Activating Token Index: 370

Text #11

Max Range: 5.6283. Min Range: -5.6283

Max Act: 5.2220. Min Act: -0.1700

Data Index: 1149873 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 5.6283. Min Range: -5.6283

Max Act: 5.1595. Min Act: -0.1700

Data Index: 1031124 (C4 (Web Text))

Max Activating Token Index: 577

Text #13

Max Range: 5.6283. Min Range: -5.6283

Max Act: 5.0345. Min Act: -0.1700

Data Index: 451131 (C4 (Web Text))

Max Activating Token Index: 915

Text #14

Max Range: 5.6283. Min Range: -5.6283

Max Act: 5.1595. Min Act: -0.1700

Data Index: 701998 (C4 (Web Text))

Max Activating Token Index: 544

Text #15

Max Range: 5.6283. Min Range: -5.6283

Max Act: 5.0345. Min Act: -0.1700

Data Index: 1166778 (C4 (Web Text))

Max Activating Token Index: 708

Text #16

Max Range: 5.6283. Min Range: -5.6283

Max Act: 5.1283. Min Act: -0.1700

Data Index: 931280 (C4 (Web Text))

Max Activating Token Index: 781

Text #17

Max Range: 5.6283. Min Range: -5.6283

Max Act: 5.0970. Min Act: -0.1700

Data Index: 226138 (C4 (Web Text))

Max Activating Token Index: 95

Text #18

Max Range: 5.6283. Min Range: -5.6283

Max Act: 5.0658. Min Act: -0.1700

Data Index: 764041 (C4 (Web Text))

Max Activating Token Index: 533

Text #19

Max Range: 5.6283. Min Range: -5.6283

Max Act: 5.0345. Min Act: -0.1700

Data Index: 584467 (C4 (Web Text))

Max Activating Token Index: 522