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

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

Neuron 396 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.6126. Min Range: -3.6126

Max Act: 3.6126. Min Act: -0.1700

Data Index: 2734 (C4 (Web Text))

Max Activating Token Index: 96

Text #1

Max Range: 3.6126. Min Range: -3.6126

Max Act: 3.5186. Min Act: -0.1700

Data Index: 122344 (C4 (Web Text))

Max Activating Token Index: 908

Text #2

Max Range: 3.6126. Min Range: -3.6126

Max Act: 3.4403. Min Act: -0.1700

Data Index: 1092187 (C4 (Web Text))

Max Activating Token Index: 809

Text #3

Max Range: 3.6126. Min Range: -3.6126

Max Act: 3.4873. Min Act: -0.1700

Data Index: 798959 (C4 (Web Text))

Max Activating Token Index: 550

Text #4

Max Range: 3.6126. Min Range: -3.6126

Max Act: 3.5030. Min Act: -0.1700

Data Index: 756226 (C4 (Web Text))

Max Activating Token Index: 323

Text #5

Max Range: 3.6126. Min Range: -3.6126

Max Act: 3.4873. Min Act: -0.1700

Data Index: 365414 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 3.6126. Min Range: -3.6126

Max Act: 3.4873. Min Act: -0.1700

Data Index: 1004354 (C4 (Web Text))

Max Activating Token Index: 829

Text #7

Max Range: 3.6126. Min Range: -3.6126

Max Act: 3.4403. Min Act: -0.1700

Data Index: 1087225 (C4 (Web Text))

Max Activating Token Index: 695

Text #8

Max Range: 3.6126. Min Range: -3.6126

Max Act: 3.4246. Min Act: -0.1700

Data Index: 7882 (C4 (Web Text))

Max Activating Token Index: 805

Text #9

Max Range: 3.6126. Min Range: -3.6126

Max Act: 3.4246. Min Act: -0.1700

Data Index: 726471 (C4 (Web Text))

Max Activating Token Index: 956

Text #10

Max Range: 3.6126. Min Range: -3.6126

Max Act: 3.4403. Min Act: -0.1700

Data Index: 1114663 (C4 (Web Text))

Max Activating Token Index: 253

Text #11

Max Range: 3.6126. Min Range: -3.6126

Max Act: 3.4403. Min Act: -0.1700

Data Index: 986697 (C4 (Web Text))

Max Activating Token Index: 950

Text #12

Max Range: 3.6126. Min Range: -3.6126

Max Act: 3.3932. Min Act: -0.1700

Data Index: 1166429 (C4 (Web Text))

Max Activating Token Index: 317

Text #13

Max Range: 3.6126. Min Range: -3.6126

Max Act: 3.4089. Min Act: -0.1700

Data Index: 778341 (C4 (Web Text))

Max Activating Token Index: 304

Text #14

Max Range: 3.6126. Min Range: -3.6126

Max Act: 3.4089. Min Act: -0.1700

Data Index: 1022834 (C4 (Web Text))

Max Activating Token Index: 600

Text #15

Max Range: 3.6126. Min Range: -3.6126

Max Act: 3.4089. Min Act: -0.1700

Data Index: 963778 (C4 (Web Text))

Max Activating Token Index: 863

Text #16

Max Range: 3.6126. Min Range: -3.6126

Max Act: 3.3932. Min Act: -0.1700

Data Index: 155982 (C4 (Web Text))

Max Activating Token Index: 1010

Text #17

Max Range: 3.6126. Min Range: -3.6126

Max Act: 3.4403. Min Act: -0.1700

Data Index: 511399 (C4 (Web Text))

Max Activating Token Index: 398

Text #18

Max Range: 3.6126. Min Range: -3.6126

Max Act: 3.3775. Min Act: -0.1700

Data Index: 1123221 (C4 (Web Text))

Max Activating Token Index: 844

Text #19

Max Range: 3.6126. Min Range: -3.6126

Max Act: 3.3775. Min Act: -0.1700

Data Index: 312049 (C4 (Web Text))

Max Activating Token Index: 372