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

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

Neuron 1647 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.2107. Min Range: -3.2107

Max Act: 3.1950. Min Act: -0.1700

Data Index: 177753 (C4 (Web Text))

Max Activating Token Index: 265

Text #1

Max Range: 3.2107. Min Range: -3.2107

Max Act: 3.1950. Min Act: -0.1700

Data Index: 86922 (C4 (Web Text))

Max Activating Token Index: 55

Text #2

Max Range: 3.2107. Min Range: -3.2107

Max Act: 3.2107. Min Act: -0.1700

Data Index: 418617 (C4 (Web Text))

Max Activating Token Index: 425

Text #3

Max Range: 3.2107. Min Range: -3.2107

Max Act: 3.1635. Min Act: -0.1700

Data Index: 724392 (C4 (Web Text))

Max Activating Token Index: 162

Text #4

Max Range: 3.2107. Min Range: -3.2107

Max Act: 3.1793. Min Act: -0.1700

Data Index: 339320 (C4 (Web Text))

Max Activating Token Index: 846

Text #5

Max Range: 3.2107. Min Range: -3.2107

Max Act: 3.1163. Min Act: -0.1700

Data Index: 218635 (C4 (Web Text))

Max Activating Token Index: 742

Text #6

Max Range: 3.2107. Min Range: -3.2107

Max Act: 3.1478. Min Act: -0.1700

Data Index: 276694 (C4 (Web Text))

Max Activating Token Index: 530

Text #7

Max Range: 3.2107. Min Range: -3.2107

Max Act: 3.1320. Min Act: -0.1700

Data Index: 572480 (C4 (Web Text))

Max Activating Token Index: 367

Text #8

Max Range: 3.2107. Min Range: -3.2107

Max Act: 3.1163. Min Act: -0.1700

Data Index: 982889 (C4 (Web Text))

Max Activating Token Index: 349

Text #9

Max Range: 3.2107. Min Range: -3.2107

Max Act: 3.0847. Min Act: -0.1700

Data Index: 871028 (C4 (Web Text))

Max Activating Token Index: 813

Text #10

Max Range: 3.2107. Min Range: -3.2107

Max Act: 3.0847. Min Act: -0.1700

Data Index: 822167 (C4 (Web Text))

Max Activating Token Index: 729

Text #11

Max Range: 3.2107. Min Range: -3.2107

Max Act: 3.1163. Min Act: -0.1700

Data Index: 915551 (C4 (Web Text))

Max Activating Token Index: 963

Text #12

Max Range: 3.2107. Min Range: -3.2107

Max Act: 3.1005. Min Act: -0.1700

Data Index: 61463 (C4 (Web Text))

Max Activating Token Index: 46

Text #13

Max Range: 3.2107. Min Range: -3.2107

Max Act: 3.1005. Min Act: -0.1700

Data Index: 427244 (C4 (Web Text))

Max Activating Token Index: 768

Text #14

Max Range: 3.2107. Min Range: -3.2107

Max Act: 3.0847. Min Act: -0.1700

Data Index: 611979 (C4 (Web Text))

Max Activating Token Index: 693

Text #15

Max Range: 3.2107. Min Range: -3.2107

Max Act: 3.0690. Min Act: -0.1700

Data Index: 606451 (C4 (Web Text))

Max Activating Token Index: 629

Text #16

Max Range: 3.2107. Min Range: -3.2107

Max Act: 3.0847. Min Act: -0.1700

Data Index: 529468 (C4 (Web Text))

Max Activating Token Index: 208

Text #17

Max Range: 3.2107. Min Range: -3.2107

Max Act: 3.0847. Min Act: -0.1700

Data Index: 1194687 (C4 (Web Text))

Max Activating Token Index: 730

Text #18

Max Range: 3.2107. Min Range: -3.2107

Max Act: 3.1005. Min Act: -0.1700

Data Index: 1224866 (C4 (Web Text))

Max Activating Token Index: 582

Text #19

Max Range: 3.2107. Min Range: -3.2107

Max Act: 3.1005. Min Act: -0.1700

Data Index: 1347874 (C4 (Web Text))

Max Activating Token Index: 330