Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1481 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.8900. Min Range: -3.8900

Max Act: 3.8900. Min Act: -0.1700

Data Index: 128142 (C4 (Web Text))

Max Activating Token Index: 236

Text #1

Max Range: 3.8900. Min Range: -3.8900

Max Act: 3.8744. Min Act: -0.1700

Data Index: 787942 (C4 (Web Text))

Max Activating Token Index: 560

Text #2

Max Range: 3.8900. Min Range: -3.8900

Max Act: 3.7649. Min Act: -0.1700

Data Index: 82637 (C4 (Web Text))

Max Activating Token Index: 943

Text #3

Max Range: 3.8900. Min Range: -3.8900

Max Act: 3.7806. Min Act: -0.1700

Data Index: 1273717 (C4 (Web Text))

Max Activating Token Index: 45

Text #4

Max Range: 3.8900. Min Range: -3.8900

Max Act: 3.7493. Min Act: -0.1700

Data Index: 198653 (C4 (Web Text))

Max Activating Token Index: 676

Text #5

Max Range: 3.8900. Min Range: -3.8900

Max Act: 3.7336. Min Act: -0.1700

Data Index: 1123725 (C4 (Web Text))

Max Activating Token Index: 193

Text #6

Max Range: 3.8900. Min Range: -3.8900

Max Act: 3.7336. Min Act: -0.1700

Data Index: 37046 (C4 (Web Text))

Max Activating Token Index: 381

Text #7

Max Range: 3.8900. Min Range: -3.8900

Max Act: 3.7023. Min Act: -0.1700

Data Index: 825996 (C4 (Web Text))

Max Activating Token Index: 376

Text #8

Max Range: 3.8900. Min Range: -3.8900

Max Act: 3.7023. Min Act: -0.1700

Data Index: 1147862 (C4 (Web Text))

Max Activating Token Index: 199

Text #9

Max Range: 3.8900. Min Range: -3.8900

Max Act: 3.6554. Min Act: -0.1700

Data Index: 715653 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 3.8900. Min Range: -3.8900

Max Act: 3.6867. Min Act: -0.1700

Data Index: 1352988 (C4 (Web Text))

Max Activating Token Index: 386

Text #11

Max Range: 3.8900. Min Range: -3.8900

Max Act: 3.6397. Min Act: -0.1700

Data Index: 506777 (C4 (Web Text))

Max Activating Token Index: 708

Text #12

Max Range: 3.8900. Min Range: -3.8900

Max Act: 3.6710. Min Act: -0.1700

Data Index: 1094112 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 3.8900. Min Range: -3.8900

Max Act: 3.6397. Min Act: -0.1700

Data Index: 567006 (C4 (Web Text))

Max Activating Token Index: 926

Text #14

Max Range: 3.8900. Min Range: -3.8900

Max Act: 3.6397. Min Act: -0.1700

Data Index: 1342946 (C4 (Web Text))

Max Activating Token Index: 837

Text #15

Max Range: 3.8900. Min Range: -3.8900

Max Act: 3.6084. Min Act: -0.1700

Data Index: 262516 (C4 (Web Text))

Max Activating Token Index: 396

Text #16

Max Range: 3.8900. Min Range: -3.8900

Max Act: 3.5615. Min Act: -0.1700

Data Index: 313528 (C4 (Web Text))

Max Activating Token Index: 510

Text #17

Max Range: 3.8900. Min Range: -3.8900

Max Act: 3.6084. Min Act: -0.1700

Data Index: 689833 (C4 (Web Text))

Max Activating Token Index: 466

Text #18

Max Range: 3.8900. Min Range: -3.8900

Max Act: 3.6084. Min Act: -0.1700

Data Index: 121339 (C4 (Web Text))

Max Activating Token Index: 358

Text #19

Max Range: 3.8900. Min Range: -3.8900

Max Act: 3.5928. Min Act: -0.1700

Data Index: 1029865 (C4 (Web Text))

Max Activating Token Index: 660