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

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

Neuron 213 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6843. Min Range: -5.6843

Max Act: 5.6843. Min Act: -0.1700

Data Index: 1279215 (C4 (Web Text))

Max Activating Token Index: 645

Text #1

Max Range: 5.6843. Min Range: -5.6843

Max Act: 5.4968. Min Act: -0.1700

Data Index: 1025397 (C4 (Web Text))

Max Activating Token Index: 979

Text #2

Max Range: 5.6843. Min Range: -5.6843

Max Act: 5.4343. Min Act: -0.1700

Data Index: 107630 (C4 (Web Text))

Max Activating Token Index: 674

Text #3

Max Range: 5.6843. Min Range: -5.6843

Max Act: 5.3093. Min Act: -0.1700

Data Index: 478936 (C4 (Web Text))

Max Activating Token Index: 573

Text #4

Max Range: 5.6843. Min Range: -5.6843

Max Act: 5.3093. Min Act: -0.1700

Data Index: 305093 (C4 (Web Text))

Max Activating Token Index: 825

Text #5

Max Range: 5.6843. Min Range: -5.6843

Max Act: 5.2781. Min Act: -0.1700

Data Index: 677468 (C4 (Web Text))

Max Activating Token Index: 274

Text #6

Max Range: 5.6843. Min Range: -5.6843

Max Act: 5.2468. Min Act: -0.1700

Data Index: 71651 (C4 (Web Text))

Max Activating Token Index: 629

Text #7

Max Range: 5.6843. Min Range: -5.6843

Max Act: 5.2781. Min Act: -0.1700

Data Index: 667079 (C4 (Web Text))

Max Activating Token Index: 203

Text #8

Max Range: 5.6843. Min Range: -5.6843

Max Act: 5.2468. Min Act: -0.1700

Data Index: 809021 (C4 (Web Text))

Max Activating Token Index: 730

Text #9

Max Range: 5.6843. Min Range: -5.6843

Max Act: 5.2156. Min Act: -0.1700

Data Index: 374058 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 5.6843. Min Range: -5.6843

Max Act: 5.1843. Min Act: -0.1700

Data Index: 791743 (C4 (Web Text))

Max Activating Token Index: 908

Text #11

Max Range: 5.6843. Min Range: -5.6843

Max Act: 5.2156. Min Act: -0.1700

Data Index: 502735 (C4 (Web Text))

Max Activating Token Index: 455

Text #12

Max Range: 5.6843. Min Range: -5.6843

Max Act: 5.1843. Min Act: -0.1700

Data Index: 291222 (C4 (Web Text))

Max Activating Token Index: 258

Text #13

Max Range: 5.6843. Min Range: -5.6843

Max Act: 5.1218. Min Act: -0.1700

Data Index: 125617 (C4 (Web Text))

Max Activating Token Index: 768

Text #14

Max Range: 5.6843. Min Range: -5.6843

Max Act: 5.1531. Min Act: -0.1700

Data Index: 6402 (C4 (Web Text))

Max Activating Token Index: 217

Text #15

Max Range: 5.6843. Min Range: -5.6843

Max Act: 5.1531. Min Act: -0.1700

Data Index: 524989 (C4 (Web Text))

Max Activating Token Index: 371

Text #16

Max Range: 5.6843. Min Range: -5.6843

Max Act: 5.1218. Min Act: -0.1700

Data Index: 1322844 (C4 (Web Text))

Max Activating Token Index: 516

Text #17

Max Range: 5.6843. Min Range: -5.6843

Max Act: 5.1531. Min Act: -0.1700

Data Index: 946621 (C4 (Web Text))

Max Activating Token Index: 580

Text #18

Max Range: 5.6843. Min Range: -5.6843

Max Act: 5.0906. Min Act: -0.1700

Data Index: 529908 (C4 (Web Text))

Max Activating Token Index: 337

Text #19

Max Range: 5.6843. Min Range: -5.6843

Max Act: 5.1218. Min Act: -0.1700

Data Index: 1233753 (C4 (Web Text))

Max Activating Token Index: 68