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

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

Neuron 1570 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: 3.7189. Min Range: -3.7189

Max Act: 3.6876. Min Act: -0.1700

Data Index: 1530702 (Python Code)

Max Activating Token Index: 438

Text #1

Max Range: 3.7189. Min Range: -3.7189

Max Act: 3.7189. Min Act: -0.1700

Data Index: 1484595 (Python Code)

Max Activating Token Index: 827

Text #2

Max Range: 3.7189. Min Range: -3.7189

Max Act: 3.7189. Min Act: -0.1700

Data Index: 1545922 (Python Code)

Max Activating Token Index: 826

Text #3

Max Range: 3.7189. Min Range: -3.7189

Max Act: 3.6876. Min Act: -0.1700

Data Index: 1390562 (Python Code)

Max Activating Token Index: 548

Text #4

Max Range: 3.7189. Min Range: -3.7189

Max Act: 3.6250. Min Act: -0.1700

Data Index: 1390856 (Python Code)

Max Activating Token Index: 673

Text #5

Max Range: 3.7189. Min Range: -3.7189

Max Act: 3.6250. Min Act: -0.1700

Data Index: 1411159 (Python Code)

Max Activating Token Index: 447

Text #6

Max Range: 3.7189. Min Range: -3.7189

Max Act: 3.6406. Min Act: -0.1700

Data Index: 1424298 (Python Code)

Max Activating Token Index: 387

Text #7

Max Range: 3.7189. Min Range: -3.7189

Max Act: 3.6563. Min Act: -0.1700

Data Index: 1538848 (Python Code)

Max Activating Token Index: 514

Text #8

Max Range: 3.7189. Min Range: -3.7189

Max Act: 3.6406. Min Act: -0.1700

Data Index: 1525106 (Python Code)

Max Activating Token Index: 384

Text #9

Max Range: 3.7189. Min Range: -3.7189

Max Act: 3.6093. Min Act: -0.1700

Data Index: 1431229 (Python Code)

Max Activating Token Index: 645

Text #10

Max Range: 3.7189. Min Range: -3.7189

Max Act: 3.5936. Min Act: -0.1700

Data Index: 1561660 (Python Code)

Max Activating Token Index: 386

Text #11

Max Range: 3.7189. Min Range: -3.7189

Max Act: 3.6250. Min Act: -0.1700

Data Index: 1564203 (Python Code)

Max Activating Token Index: 715

Text #12

Max Range: 3.7189. Min Range: -3.7189

Max Act: 3.6250. Min Act: -0.1700

Data Index: 1464676 (Python Code)

Max Activating Token Index: 626

Text #13

Max Range: 3.7189. Min Range: -3.7189

Max Act: 3.5780. Min Act: -0.1700

Data Index: 1471687 (Python Code)

Max Activating Token Index: 269

Text #14

Max Range: 3.7189. Min Range: -3.7189

Max Act: 3.5936. Min Act: -0.1700

Data Index: 1380002 (Python Code)

Max Activating Token Index: 827

Text #15

Max Range: 3.7189. Min Range: -3.7189

Max Act: 3.5623. Min Act: -0.1700

Data Index: 1428158 (Python Code)

Max Activating Token Index: 203

Text #16

Max Range: 3.7189. Min Range: -3.7189

Max Act: 3.5780. Min Act: -0.1700

Data Index: 1520490 (Python Code)

Max Activating Token Index: 823

Text #17

Max Range: 3.7189. Min Range: -3.7189

Max Act: 3.6093. Min Act: -0.1700

Data Index: 1442975 (Python Code)

Max Activating Token Index: 582

Text #18

Max Range: 3.7189. Min Range: -3.7189

Max Act: 3.5936. Min Act: -0.1700

Data Index: 1457118 (Python Code)

Max Activating Token Index: 788

Text #19

Max Range: 3.7189. Min Range: -3.7189

Max Act: 3.6093. Min Act: -0.1700

Data Index: 1632681 (Python Code)

Max Activating Token Index: 250