Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 970 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.6886. Min Range: -3.6886

Max Act: 3.6886. Min Act: -0.1700

Data Index: 486694 (C4 (Web Text))

Max Activating Token Index: 640

Text #1

Max Range: 3.6886. Min Range: -3.6886

Max Act: 3.6809. Min Act: -0.1700

Data Index: 381870 (C4 (Web Text))

Max Activating Token Index: 350

Text #2

Max Range: 3.6886. Min Range: -3.6886

Max Act: 3.6654. Min Act: -0.1692

Data Index: 648715 (C4 (Web Text))

Max Activating Token Index: 428

Text #3

Max Range: 3.6886. Min Range: -3.6886

Max Act: 3.6320. Min Act: -0.1700

Data Index: 210178 (C4 (Web Text))

Max Activating Token Index: 83

Text #4

Max Range: 3.6886. Min Range: -3.6886

Max Act: 3.6421. Min Act: -0.1700

Data Index: 1190903 (C4 (Web Text))

Max Activating Token Index: 87

Text #5

Max Range: 3.6886. Min Range: -3.6886

Max Act: 3.6385. Min Act: -0.1700

Data Index: 263224 (C4 (Web Text))

Max Activating Token Index: 1006

Text #6

Max Range: 3.6886. Min Range: -3.6886

Max Act: 3.5957. Min Act: -0.1664

Data Index: 33958 (C4 (Web Text))

Max Activating Token Index: 419

Text #7

Max Range: 3.6886. Min Range: -3.6886

Max Act: 3.6134. Min Act: -0.1700

Data Index: 396602 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 3.6886. Min Range: -3.6886

Max Act: 3.6221. Min Act: -0.1699

Data Index: 431989 (C4 (Web Text))

Max Activating Token Index: 594

Text #9

Max Range: 3.6886. Min Range: -3.6886

Max Act: 3.6228. Min Act: -0.1700

Data Index: 162982 (C4 (Web Text))

Max Activating Token Index: 612

Text #10

Max Range: 3.6886. Min Range: -3.6886

Max Act: 3.5822. Min Act: -0.1699

Data Index: 1184414 (C4 (Web Text))

Max Activating Token Index: 544

Text #11

Max Range: 3.6886. Min Range: -3.6886

Max Act: 3.5654. Min Act: -0.1700

Data Index: 1134921 (C4 (Web Text))

Max Activating Token Index: 156

Text #12

Max Range: 3.6886. Min Range: -3.6886

Max Act: 3.5809. Min Act: -0.1700

Data Index: 725474 (C4 (Web Text))

Max Activating Token Index: 403

Text #13

Max Range: 3.6886. Min Range: -3.6886

Max Act: 3.5589. Min Act: -0.1700

Data Index: 606097 (C4 (Web Text))

Max Activating Token Index: 585

Text #14

Max Range: 3.6886. Min Range: -3.6886

Max Act: 3.5442. Min Act: -0.1700

Data Index: 171707 (C4 (Web Text))

Max Activating Token Index: 392

Text #15

Max Range: 3.6886. Min Range: -3.6886

Max Act: 3.5373. Min Act: -0.1700

Data Index: 26030 (C4 (Web Text))

Max Activating Token Index: 426

Text #16

Max Range: 3.6886. Min Range: -3.6886

Max Act: 3.5414. Min Act: -0.1699

Data Index: 1182890 (C4 (Web Text))

Max Activating Token Index: 373

Text #17

Max Range: 3.6886. Min Range: -3.6886

Max Act: 3.5207. Min Act: -0.1700

Data Index: 307996 (C4 (Web Text))

Max Activating Token Index: 899

Text #18

Max Range: 3.6886. Min Range: -3.6886

Max Act: 3.5368. Min Act: -0.1700

Data Index: 92669 (C4 (Web Text))

Max Activating Token Index: 494

Text #19

Max Range: 3.6886. Min Range: -3.6886

Max Act: 3.5091. Min Act: -0.1700

Data Index: 1315887 (C4 (Web Text))

Max Activating Token Index: 420