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

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

Neuron 903 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: 3.7575. Min Range: -3.7575

Max Act: 3.7575. Min Act: -0.1700

Data Index: 1118470 (C4 (Web Text))

Max Activating Token Index: 638

Text #1

Max Range: 3.7575. Min Range: -3.7575

Max Act: 3.6792. Min Act: -0.1700

Data Index: 109805 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.7575. Min Range: -3.7575

Max Act: 3.5383. Min Act: -0.1700

Data Index: 386417 (C4 (Web Text))

Max Activating Token Index: 700

Text #3

Max Range: 3.7575. Min Range: -3.7575

Max Act: 3.5070. Min Act: -0.1700

Data Index: 907175 (C4 (Web Text))

Max Activating Token Index: 22

Text #4

Max Range: 3.7575. Min Range: -3.7575

Max Act: 3.4913. Min Act: -0.1700

Data Index: 443553 (C4 (Web Text))

Max Activating Token Index: 545

Text #5

Max Range: 3.7575. Min Range: -3.7575

Max Act: 3.4756. Min Act: -0.1700

Data Index: 29712 (C4 (Web Text))

Max Activating Token Index: 328

Text #6

Max Range: 3.7575. Min Range: -3.7575

Max Act: 3.4600. Min Act: -0.1700

Data Index: 578044 (C4 (Web Text))

Max Activating Token Index: 118

Text #7

Max Range: 3.7575. Min Range: -3.7575

Max Act: 3.4443. Min Act: -0.1700

Data Index: 1156433 (C4 (Web Text))

Max Activating Token Index: 19

Text #8

Max Range: 3.7575. Min Range: -3.7575

Max Act: 3.4756. Min Act: -0.1700

Data Index: 483448 (C4 (Web Text))

Max Activating Token Index: 1006

Text #9

Max Range: 3.7575. Min Range: -3.7575

Max Act: 3.4600. Min Act: -0.1700

Data Index: 448284 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 3.7575. Min Range: -3.7575

Max Act: 3.4286. Min Act: -0.1700

Data Index: 1079918 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 3.7575. Min Range: -3.7575

Max Act: 3.4129. Min Act: -0.1700

Data Index: 1008199 (C4 (Web Text))

Max Activating Token Index: 661

Text #12

Max Range: 3.7575. Min Range: -3.7575

Max Act: 3.4286. Min Act: -0.1700

Data Index: 430794 (C4 (Web Text))

Max Activating Token Index: 141

Text #13

Max Range: 3.7575. Min Range: -3.7575

Max Act: 3.4286. Min Act: -0.1700

Data Index: 267763 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 3.7575. Min Range: -3.7575

Max Act: 3.3816. Min Act: -0.1700

Data Index: 82200 (C4 (Web Text))

Max Activating Token Index: 447

Text #15

Max Range: 3.7575. Min Range: -3.7575

Max Act: 3.4129. Min Act: -0.1700

Data Index: 1540371 (Python Code)

Max Activating Token Index: 623

Text #16

Max Range: 3.7575. Min Range: -3.7575

Max Act: 3.4129. Min Act: -0.1700

Data Index: 1063156 (C4 (Web Text))

Max Activating Token Index: 982

Text #17

Max Range: 3.7575. Min Range: -3.7575

Max Act: 3.4286. Min Act: -0.1700

Data Index: 783383 (C4 (Web Text))

Max Activating Token Index: 62

Text #18

Max Range: 3.7575. Min Range: -3.7575

Max Act: 3.4286. Min Act: -0.1700

Data Index: 360716 (C4 (Web Text))

Max Activating Token Index: 534

Text #19

Max Range: 3.7575. Min Range: -3.7575

Max Act: 3.4443. Min Act: -0.1700

Data Index: 956241 (C4 (Web Text))

Max Activating Token Index: 283