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

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

Neuron 1479 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: 3.3789. Min Range: -3.3789

Max Act: 3.3789. Min Act: -0.1700

Data Index: 468655 (C4 (Web Text))

Max Activating Token Index: 88

Text #1

Max Range: 3.3789. Min Range: -3.3789

Max Act: 3.3318. Min Act: -0.1700

Data Index: 1149611 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.3789. Min Range: -3.3789

Max Act: 3.2690. Min Act: -0.1700

Data Index: 470260 (C4 (Web Text))

Max Activating Token Index: 869

Text #3

Max Range: 3.3789. Min Range: -3.3789

Max Act: 3.2375. Min Act: -0.1700

Data Index: 1178878 (C4 (Web Text))

Max Activating Token Index: 331

Text #4

Max Range: 3.3789. Min Range: -3.3789

Max Act: 3.2375. Min Act: -0.1700

Data Index: 828517 (C4 (Web Text))

Max Activating Token Index: 11

Text #5

Max Range: 3.3789. Min Range: -3.3789

Max Act: 3.2061. Min Act: -0.1700

Data Index: 607046 (C4 (Web Text))

Max Activating Token Index: 707

Text #6

Max Range: 3.3789. Min Range: -3.3789

Max Act: 3.2061. Min Act: -0.1700

Data Index: 298549 (C4 (Web Text))

Max Activating Token Index: 570

Text #7

Max Range: 3.3789. Min Range: -3.3789

Max Act: 3.1746. Min Act: -0.1700

Data Index: 391628 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 3.3789. Min Range: -3.3789

Max Act: 3.1431. Min Act: -0.1700

Data Index: 267887 (C4 (Web Text))

Max Activating Token Index: 385

Text #9

Max Range: 3.3789. Min Range: -3.3789

Max Act: 3.0643. Min Act: -0.1700

Data Index: 708278 (C4 (Web Text))

Max Activating Token Index: 383

Text #10

Max Range: 3.3789. Min Range: -3.3789

Max Act: 3.0643. Min Act: -0.1700

Data Index: 245536 (C4 (Web Text))

Max Activating Token Index: 178

Text #11

Max Range: 3.3789. Min Range: -3.3789

Max Act: 3.0643. Min Act: -0.1700

Data Index: 200886 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 3.3789. Min Range: -3.3789

Max Act: 3.0327. Min Act: -0.1700

Data Index: 25664 (C4 (Web Text))

Max Activating Token Index: 934

Text #13

Max Range: 3.3789. Min Range: -3.3789

Max Act: 2.9695. Min Act: -0.1700

Data Index: 1228940 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 3.3789. Min Range: -3.3789

Max Act: 2.9536. Min Act: -0.1700

Data Index: 986643 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 3.3789. Min Range: -3.3789

Max Act: 2.9378. Min Act: -0.1700

Data Index: 1357112 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 3.3789. Min Range: -3.3789

Max Act: 2.9061. Min Act: -0.1700

Data Index: 419643 (C4 (Web Text))

Max Activating Token Index: 989

Text #17

Max Range: 3.3789. Min Range: -3.3789

Max Act: 2.9061. Min Act: -0.1700

Data Index: 575007 (C4 (Web Text))

Max Activating Token Index: 460

Text #18

Max Range: 3.3789. Min Range: -3.3789

Max Act: 2.8902. Min Act: -0.1700

Data Index: 1257579 (C4 (Web Text))

Max Activating Token Index: 185

Text #19

Max Range: 3.3789. Min Range: -3.3789

Max Act: 2.9061. Min Act: -0.1700

Data Index: 1204966 (C4 (Web Text))

Max Activating Token Index: 730