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

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

Neuron 738 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3239. Min Range: -3.3239

Max Act: 3.2925. Min Act: -0.1700

Data Index: 1076516 (C4 (Web Text))

Max Activating Token Index: 581

Text #1

Max Range: 3.3239. Min Range: -3.3239

Max Act: 3.3239. Min Act: -0.1700

Data Index: 818300 (C4 (Web Text))

Max Activating Token Index: 856

Text #2

Max Range: 3.3239. Min Range: -3.3239

Max Act: 3.2611. Min Act: -0.1700

Data Index: 1256693 (C4 (Web Text))

Max Activating Token Index: 746

Text #3

Max Range: 3.3239. Min Range: -3.3239

Max Act: 3.2925. Min Act: -0.1700

Data Index: 1232238 (C4 (Web Text))

Max Activating Token Index: 321

Text #4

Max Range: 3.3239. Min Range: -3.3239

Max Act: 3.2925. Min Act: -0.1700

Data Index: 112323 (C4 (Web Text))

Max Activating Token Index: 140

Text #5

Max Range: 3.3239. Min Range: -3.3239

Max Act: 3.2611. Min Act: -0.1700

Data Index: 743547 (C4 (Web Text))

Max Activating Token Index: 277

Text #6

Max Range: 3.3239. Min Range: -3.3239

Max Act: 3.2453. Min Act: -0.1700

Data Index: 961447 (C4 (Web Text))

Max Activating Token Index: 988

Text #7

Max Range: 3.3239. Min Range: -3.3239

Max Act: 3.2296. Min Act: -0.1700

Data Index: 961769 (C4 (Web Text))

Max Activating Token Index: 135

Text #8

Max Range: 3.3239. Min Range: -3.3239

Max Act: 3.1982. Min Act: -0.1700

Data Index: 389228 (C4 (Web Text))

Max Activating Token Index: 769

Text #9

Max Range: 3.3239. Min Range: -3.3239

Max Act: 3.2296. Min Act: -0.1700

Data Index: 18287 (C4 (Web Text))

Max Activating Token Index: 963

Text #10

Max Range: 3.3239. Min Range: -3.3239

Max Act: 3.2296. Min Act: -0.1700

Data Index: 1093483 (C4 (Web Text))

Max Activating Token Index: 417

Text #11

Max Range: 3.3239. Min Range: -3.3239

Max Act: 3.1824. Min Act: -0.1700

Data Index: 600098 (C4 (Web Text))

Max Activating Token Index: 641

Text #12

Max Range: 3.3239. Min Range: -3.3239

Max Act: 3.2139. Min Act: -0.1700

Data Index: 616263 (C4 (Web Text))

Max Activating Token Index: 338

Text #13

Max Range: 3.3239. Min Range: -3.3239

Max Act: 3.1982. Min Act: -0.1700

Data Index: 1107163 (C4 (Web Text))

Max Activating Token Index: 990

Text #14

Max Range: 3.3239. Min Range: -3.3239

Max Act: 3.1667. Min Act: -0.1700

Data Index: 890948 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 3.3239. Min Range: -3.3239

Max Act: 3.1824. Min Act: -0.1700

Data Index: 1072213 (C4 (Web Text))

Max Activating Token Index: 960

Text #16

Max Range: 3.3239. Min Range: -3.3239

Max Act: 3.1824. Min Act: -0.1700

Data Index: 1101901 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 3.3239. Min Range: -3.3239

Max Act: 3.1667. Min Act: -0.1700

Data Index: 1150929 (C4 (Web Text))

Max Activating Token Index: 952

Text #18

Max Range: 3.3239. Min Range: -3.3239

Max Act: 3.1352. Min Act: -0.1700

Data Index: 236242 (C4 (Web Text))

Max Activating Token Index: 146

Text #19

Max Range: 3.3239. Min Range: -3.3239

Max Act: 3.1667. Min Act: -0.1700

Data Index: 1156160 (C4 (Web Text))

Max Activating Token Index: 793