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

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

Neuron 1617 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: 3.7922. Min Range: -3.7922

Max Act: 3.7765. Min Act: -0.1700

Data Index: 131466 (C4 (Web Text))

Max Activating Token Index: 294

Text #1

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.7922. Min Act: -0.1700

Data Index: 170345 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.7452. Min Act: -0.1700

Data Index: 37866 (C4 (Web Text))

Max Activating Token Index: 361

Text #3

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.7452. Min Act: -0.1700

Data Index: 62092 (C4 (Web Text))

Max Activating Token Index: 543

Text #4

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.6983. Min Act: -0.1700

Data Index: 380111 (C4 (Web Text))

Max Activating Token Index: 514

Text #5

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.6983. Min Act: -0.1700

Data Index: 986391 (C4 (Web Text))

Max Activating Token Index: 878

Text #6

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.6670. Min Act: -0.1700

Data Index: 1025534 (C4 (Web Text))

Max Activating Token Index: 634

Text #7

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.6513. Min Act: -0.1700

Data Index: 823995 (C4 (Web Text))

Max Activating Token Index: 534

Text #8

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.6357. Min Act: -0.1700

Data Index: 167456 (C4 (Web Text))

Max Activating Token Index: 337

Text #9

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.6513. Min Act: -0.1700

Data Index: 598031 (C4 (Web Text))

Max Activating Token Index: 248

Text #10

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.6357. Min Act: -0.1700

Data Index: 147013 (C4 (Web Text))

Max Activating Token Index: 916

Text #11

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.6513. Min Act: -0.1700

Data Index: 477440 (C4 (Web Text))

Max Activating Token Index: 657

Text #12

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.6200. Min Act: -0.1700

Data Index: 875925 (C4 (Web Text))

Max Activating Token Index: 504

Text #13

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.6357. Min Act: -0.1700

Data Index: 188660 (C4 (Web Text))

Max Activating Token Index: 5

Text #14

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.5887. Min Act: -0.1700

Data Index: 840688 (C4 (Web Text))

Max Activating Token Index: 137

Text #15

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.6044. Min Act: -0.1700

Data Index: 1167816 (C4 (Web Text))

Max Activating Token Index: 138

Text #16

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.6044. Min Act: -0.1700

Data Index: 528786 (C4 (Web Text))

Max Activating Token Index: 185

Text #17

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.6044. Min Act: -0.1700

Data Index: 1330237 (C4 (Web Text))

Max Activating Token Index: 17

Text #18

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.5887. Min Act: -0.1700

Data Index: 265839 (C4 (Web Text))

Max Activating Token Index: 163

Text #19

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.5887. Min Act: -0.1700

Data Index: 56885 (C4 (Web Text))

Max Activating Token Index: 616