Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 67 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.6312. Min Range: -3.6312

Max Act: 3.6312. Min Act: -0.1700

Data Index: 1164289 (C4 (Web Text))

Max Activating Token Index: 361

Text #1

Max Range: 3.6312. Min Range: -3.6312

Max Act: 3.6156. Min Act: -0.1700

Data Index: 395909 (C4 (Web Text))

Max Activating Token Index: 616

Text #2

Max Range: 3.6312. Min Range: -3.6312

Max Act: 3.5999. Min Act: -0.1700

Data Index: 276004 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 3.6312. Min Range: -3.6312

Max Act: 3.5842. Min Act: -0.1700

Data Index: 942727 (C4 (Web Text))

Max Activating Token Index: 177

Text #4

Max Range: 3.6312. Min Range: -3.6312

Max Act: 3.5999. Min Act: -0.1700

Data Index: 954836 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 3.6312. Min Range: -3.6312

Max Act: 3.5842. Min Act: -0.1700

Data Index: 129041 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 3.6312. Min Range: -3.6312

Max Act: 3.5686. Min Act: -0.1700

Data Index: 1038045 (C4 (Web Text))

Max Activating Token Index: 642

Text #7

Max Range: 3.6312. Min Range: -3.6312

Max Act: 3.5686. Min Act: -0.1700

Data Index: 357574 (C4 (Web Text))

Max Activating Token Index: 59

Text #8

Max Range: 3.6312. Min Range: -3.6312

Max Act: 3.5686. Min Act: -0.1700

Data Index: 1347881 (C4 (Web Text))

Max Activating Token Index: 339

Text #9

Max Range: 3.6312. Min Range: -3.6312

Max Act: 3.5842. Min Act: -0.1700

Data Index: 795047 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 3.6312. Min Range: -3.6312

Max Act: 3.5686. Min Act: -0.1700

Data Index: 620846 (C4 (Web Text))

Max Activating Token Index: 773

Text #11

Max Range: 3.6312. Min Range: -3.6312

Max Act: 3.5529. Min Act: -0.1700

Data Index: 882601 (C4 (Web Text))

Max Activating Token Index: 937

Text #12

Max Range: 3.6312. Min Range: -3.6312

Max Act: 3.5373. Min Act: -0.1700

Data Index: 628914 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 3.6312. Min Range: -3.6312

Max Act: 3.5373. Min Act: -0.1700

Data Index: 637585 (C4 (Web Text))

Max Activating Token Index: 111

Text #14

Max Range: 3.6312. Min Range: -3.6312

Max Act: 3.5373. Min Act: -0.1700

Data Index: 612597 (C4 (Web Text))

Max Activating Token Index: 114

Text #15

Max Range: 3.6312. Min Range: -3.6312

Max Act: 3.5373. Min Act: -0.1700

Data Index: 1159827 (C4 (Web Text))

Max Activating Token Index: 76

Text #16

Max Range: 3.6312. Min Range: -3.6312

Max Act: 3.5373. Min Act: -0.1700

Data Index: 765875 (C4 (Web Text))

Max Activating Token Index: 763

Text #17

Max Range: 3.6312. Min Range: -3.6312

Max Act: 3.5373. Min Act: -0.1700

Data Index: 1000169 (C4 (Web Text))

Max Activating Token Index: 473

Text #18

Max Range: 3.6312. Min Range: -3.6312

Max Act: 3.5373. Min Act: -0.1700

Data Index: 1018178 (C4 (Web Text))

Max Activating Token Index: 152

Text #19

Max Range: 3.6312. Min Range: -3.6312

Max Act: 3.5373. Min Act: -0.1700

Data Index: 1343403 (C4 (Web Text))

Max Activating Token Index: 88