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

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

Neuron 1071 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: 3.2879. Min Range: -3.2879

Max Act: 3.2879. Min Act: -0.1700

Data Index: 1303580 (C4 (Web Text))

Max Activating Token Index: 747

Text #1

Max Range: 3.2879. Min Range: -3.2879

Max Act: 3.2408. Min Act: -0.1700

Data Index: 699494 (C4 (Web Text))

Max Activating Token Index: 796

Text #2

Max Range: 3.2879. Min Range: -3.2879

Max Act: 3.1778. Min Act: -0.1700

Data Index: 88370 (C4 (Web Text))

Max Activating Token Index: 852

Text #3

Max Range: 3.2879. Min Range: -3.2879

Max Act: 3.2250. Min Act: -0.1700

Data Index: 682484 (C4 (Web Text))

Max Activating Token Index: 244

Text #4

Max Range: 3.2879. Min Range: -3.2879

Max Act: 3.1148. Min Act: -0.1700

Data Index: 516840 (C4 (Web Text))

Max Activating Token Index: 628

Text #5

Max Range: 3.2879. Min Range: -3.2879

Max Act: 3.0517. Min Act: -0.1700

Data Index: 1058420 (C4 (Web Text))

Max Activating Token Index: 411

Text #6

Max Range: 3.2879. Min Range: -3.2879

Max Act: 2.9885. Min Act: -0.1700

Data Index: 1220633 (C4 (Web Text))

Max Activating Token Index: 474

Text #7

Max Range: 3.2879. Min Range: -3.2879

Max Act: 3.0202. Min Act: -0.1700

Data Index: 242631 (C4 (Web Text))

Max Activating Token Index: 808

Text #8

Max Range: 3.2879. Min Range: -3.2879

Max Act: 3.0044. Min Act: -0.1700

Data Index: 1185777 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 3.2879. Min Range: -3.2879

Max Act: 2.9727. Min Act: -0.1700

Data Index: 537512 (C4 (Web Text))

Max Activating Token Index: 979

Text #10

Max Range: 3.2879. Min Range: -3.2879

Max Act: 3.0044. Min Act: -0.1700

Data Index: 271737 (C4 (Web Text))

Max Activating Token Index: 147

Text #11

Max Range: 3.2879. Min Range: -3.2879

Max Act: 2.9727. Min Act: -0.1700

Data Index: 1357755 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 3.2879. Min Range: -3.2879

Max Act: 3.0044. Min Act: -0.1700

Data Index: 194418 (C4 (Web Text))

Max Activating Token Index: 687

Text #13

Max Range: 3.2879. Min Range: -3.2879

Max Act: 2.9727. Min Act: -0.1700

Data Index: 690755 (C4 (Web Text))

Max Activating Token Index: 452

Text #14

Max Range: 3.2879. Min Range: -3.2879

Max Act: 2.9885. Min Act: -0.1700

Data Index: 776274 (C4 (Web Text))

Max Activating Token Index: 883

Text #15

Max Range: 3.2879. Min Range: -3.2879

Max Act: 2.9727. Min Act: -0.1700

Data Index: 1103216 (C4 (Web Text))

Max Activating Token Index: 348

Text #16

Max Range: 3.2879. Min Range: -3.2879

Max Act: 2.9727. Min Act: -0.1700

Data Index: 691985 (C4 (Web Text))

Max Activating Token Index: 739

Text #17

Max Range: 3.2879. Min Range: -3.2879

Max Act: 2.9727. Min Act: -0.1700

Data Index: 21034 (C4 (Web Text))

Max Activating Token Index: 998

Text #18

Max Range: 3.2879. Min Range: -3.2879

Max Act: 3.0044. Min Act: -0.1700

Data Index: 744047 (C4 (Web Text))

Max Activating Token Index: 683

Text #19

Max Range: 3.2879. Min Range: -3.2879

Max Act: 2.9569. Min Act: -0.1700

Data Index: 752649 (C4 (Web Text))

Max Activating Token Index: 643