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

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

Neuron 1373 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8710. Min Range: -3.8710

Max Act: 3.7772. Min Act: -0.1700

Data Index: 1189474 (C4 (Web Text))

Max Activating Token Index: 797

Text #1

Max Range: 3.8710. Min Range: -3.8710

Max Act: 3.8085. Min Act: -0.1700

Data Index: 708923 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.8710. Min Range: -3.8710

Max Act: 3.8710. Min Act: -0.1700

Data Index: 109810 (C4 (Web Text))

Max Activating Token Index: 655

Text #3

Max Range: 3.8710. Min Range: -3.8710

Max Act: 3.7772. Min Act: -0.1700

Data Index: 1174651 (C4 (Web Text))

Max Activating Token Index: 626

Text #4

Max Range: 3.8710. Min Range: -3.8710

Max Act: 3.7459. Min Act: -0.1700

Data Index: 285240 (C4 (Web Text))

Max Activating Token Index: 350

Text #5

Max Range: 3.8710. Min Range: -3.8710

Max Act: 3.7772. Min Act: -0.1700

Data Index: 1030483 (C4 (Web Text))

Max Activating Token Index: 76

Text #6

Max Range: 3.8710. Min Range: -3.8710

Max Act: 3.7772. Min Act: -0.1700

Data Index: 143 (C4 (Web Text))

Max Activating Token Index: 203

Text #7

Max Range: 3.8710. Min Range: -3.8710

Max Act: 3.7772. Min Act: -0.1700

Data Index: 1099570 (C4 (Web Text))

Max Activating Token Index: 832

Text #8

Max Range: 3.8710. Min Range: -3.8710

Max Act: 3.7459. Min Act: -0.1700

Data Index: 1310634 (C4 (Web Text))

Max Activating Token Index: 244

Text #9

Max Range: 3.8710. Min Range: -3.8710

Max Act: 3.7146. Min Act: -0.1700

Data Index: 721216 (C4 (Web Text))

Max Activating Token Index: 1011

Text #10

Max Range: 3.8710. Min Range: -3.8710

Max Act: 3.7459. Min Act: -0.1700

Data Index: 803675 (C4 (Web Text))

Max Activating Token Index: 823

Text #11

Max Range: 3.8710. Min Range: -3.8710

Max Act: 3.6677. Min Act: -0.1700

Data Index: 363495 (C4 (Web Text))

Max Activating Token Index: 194

Text #12

Max Range: 3.8710. Min Range: -3.8710

Max Act: 3.7459. Min Act: -0.1700

Data Index: 1060674 (C4 (Web Text))

Max Activating Token Index: 939

Text #13

Max Range: 3.8710. Min Range: -3.8710

Max Act: 3.8085. Min Act: -0.1700

Data Index: 1067425 (C4 (Web Text))

Max Activating Token Index: 942

Text #14

Max Range: 3.8710. Min Range: -3.8710

Max Act: 3.7146. Min Act: -0.1700

Data Index: 479078 (C4 (Web Text))

Max Activating Token Index: 796

Text #15

Max Range: 3.8710. Min Range: -3.8710

Max Act: 3.7146. Min Act: -0.1700

Data Index: 314514 (C4 (Web Text))

Max Activating Token Index: 122

Text #16

Max Range: 3.8710. Min Range: -3.8710

Max Act: 3.7146. Min Act: -0.1700

Data Index: 417454 (C4 (Web Text))

Max Activating Token Index: 915

Text #17

Max Range: 3.8710. Min Range: -3.8710

Max Act: 3.6833. Min Act: -0.1700

Data Index: 321050 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 3.8710. Min Range: -3.8710

Max Act: 3.7459. Min Act: -0.1700

Data Index: 420723 (C4 (Web Text))

Max Activating Token Index: 207

Text #19

Max Range: 3.8710. Min Range: -3.8710

Max Act: 3.6833. Min Act: -0.1700

Data Index: 446138 (C4 (Web Text))

Max Activating Token Index: 577