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

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

Neuron 1771 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: 3.3678. Min Range: -3.3678

Max Act: 3.3678. Min Act: -0.1700

Data Index: 715474 (C4 (Web Text))

Max Activating Token Index: 899

Text #1

Max Range: 3.3678. Min Range: -3.3678

Max Act: 3.2893. Min Act: -0.1700

Data Index: 726542 (C4 (Web Text))

Max Activating Token Index: 288

Text #2

Max Range: 3.3678. Min Range: -3.3678

Max Act: 3.2422. Min Act: -0.1700

Data Index: 331392 (C4 (Web Text))

Max Activating Token Index: 306

Text #3

Max Range: 3.3678. Min Range: -3.3678

Max Act: 3.2422. Min Act: -0.1700

Data Index: 542465 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 3.3678. Min Range: -3.3678

Max Act: 3.2265. Min Act: -0.1700

Data Index: 1194342 (C4 (Web Text))

Max Activating Token Index: 543

Text #5

Max Range: 3.3678. Min Range: -3.3678

Max Act: 3.2579. Min Act: -0.1700

Data Index: 128894 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 3.3678. Min Range: -3.3678

Max Act: 3.2265. Min Act: -0.1700

Data Index: 1335116 (C4 (Web Text))

Max Activating Token Index: 994

Text #7

Max Range: 3.3678. Min Range: -3.3678

Max Act: 3.2422. Min Act: -0.1700

Data Index: 360790 (C4 (Web Text))

Max Activating Token Index: 574

Text #8

Max Range: 3.3678. Min Range: -3.3678

Max Act: 3.2107. Min Act: -0.1700

Data Index: 1296732 (C4 (Web Text))

Max Activating Token Index: 309

Text #9

Max Range: 3.3678. Min Range: -3.3678

Max Act: 3.2265. Min Act: -0.1700

Data Index: 108416 (C4 (Web Text))

Max Activating Token Index: 627

Text #10

Max Range: 3.3678. Min Range: -3.3678

Max Act: 3.2107. Min Act: -0.1700

Data Index: 571966 (C4 (Web Text))

Max Activating Token Index: 226

Text #11

Max Range: 3.3678. Min Range: -3.3678

Max Act: 3.2107. Min Act: -0.1700

Data Index: 1295255 (C4 (Web Text))

Max Activating Token Index: 419

Text #12

Max Range: 3.3678. Min Range: -3.3678

Max Act: 3.1950. Min Act: -0.1700

Data Index: 370754 (C4 (Web Text))

Max Activating Token Index: 877

Text #13

Max Range: 3.3678. Min Range: -3.3678

Max Act: 3.1950. Min Act: -0.1700

Data Index: 661918 (C4 (Web Text))

Max Activating Token Index: 182

Text #14

Max Range: 3.3678. Min Range: -3.3678

Max Act: 3.1950. Min Act: -0.1700

Data Index: 393281 (C4 (Web Text))

Max Activating Token Index: 349

Text #15

Max Range: 3.3678. Min Range: -3.3678

Max Act: 3.1635. Min Act: -0.1700

Data Index: 678140 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 3.3678. Min Range: -3.3678

Max Act: 3.1950. Min Act: -0.1700

Data Index: 273930 (C4 (Web Text))

Max Activating Token Index: 647

Text #17

Max Range: 3.3678. Min Range: -3.3678

Max Act: 3.2107. Min Act: -0.1700

Data Index: 257296 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 3.3678. Min Range: -3.3678

Max Act: 3.1793. Min Act: -0.1700

Data Index: 291871 (C4 (Web Text))

Max Activating Token Index: 408

Text #19

Max Range: 3.3678. Min Range: -3.3678

Max Act: 3.1793. Min Act: -0.1700

Data Index: 681732 (C4 (Web Text))

Max Activating Token Index: 575