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

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

Neuron 510 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: 3.7269. Min Range: -3.7269

Max Act: 3.7113. Min Act: -0.1700

Data Index: 1139083 (C4 (Web Text))

Max Activating Token Index: 205

Text #1

Max Range: 3.7269. Min Range: -3.7269

Max Act: 3.7269. Min Act: -0.1700

Data Index: 909494 (C4 (Web Text))

Max Activating Token Index: 898

Text #2

Max Range: 3.7269. Min Range: -3.7269

Max Act: 3.6643. Min Act: -0.1700

Data Index: 196612 (C4 (Web Text))

Max Activating Token Index: 131

Text #3

Max Range: 3.7269. Min Range: -3.7269

Max Act: 3.6487. Min Act: -0.1700

Data Index: 464965 (C4 (Web Text))

Max Activating Token Index: 786

Text #4

Max Range: 3.7269. Min Range: -3.7269

Max Act: 3.6487. Min Act: -0.1700

Data Index: 907909 (C4 (Web Text))

Max Activating Token Index: 868

Text #5

Max Range: 3.7269. Min Range: -3.7269

Max Act: 3.5860. Min Act: -0.1700

Data Index: 640913 (C4 (Web Text))

Max Activating Token Index: 685

Text #6

Max Range: 3.7269. Min Range: -3.7269

Max Act: 3.6330. Min Act: -0.1700

Data Index: 662628 (C4 (Web Text))

Max Activating Token Index: 57

Text #7

Max Range: 3.7269. Min Range: -3.7269

Max Act: 3.6174. Min Act: -0.1700

Data Index: 612205 (C4 (Web Text))

Max Activating Token Index: 149

Text #8

Max Range: 3.7269. Min Range: -3.7269

Max Act: 3.5860. Min Act: -0.1700

Data Index: 425386 (C4 (Web Text))

Max Activating Token Index: 714

Text #9

Max Range: 3.7269. Min Range: -3.7269

Max Act: 3.6017. Min Act: -0.1700

Data Index: 708000 (C4 (Web Text))

Max Activating Token Index: 893

Text #10

Max Range: 3.7269. Min Range: -3.7269

Max Act: 3.6174. Min Act: -0.1700

Data Index: 1021694 (C4 (Web Text))

Max Activating Token Index: 694

Text #11

Max Range: 3.7269. Min Range: -3.7269

Max Act: 3.6017. Min Act: -0.1700

Data Index: 1337156 (C4 (Web Text))

Max Activating Token Index: 604

Text #12

Max Range: 3.7269. Min Range: -3.7269

Max Act: 3.5391. Min Act: -0.1700

Data Index: 505047 (C4 (Web Text))

Max Activating Token Index: 542

Text #13

Max Range: 3.7269. Min Range: -3.7269

Max Act: 3.6017. Min Act: -0.1700

Data Index: 1052806 (C4 (Web Text))

Max Activating Token Index: 1019

Text #14

Max Range: 3.7269. Min Range: -3.7269

Max Act: 3.5077. Min Act: -0.1700

Data Index: 331613 (C4 (Web Text))

Max Activating Token Index: 367

Text #15

Max Range: 3.7269. Min Range: -3.7269

Max Act: 3.5391. Min Act: -0.1700

Data Index: 976242 (C4 (Web Text))

Max Activating Token Index: 465

Text #16

Max Range: 3.7269. Min Range: -3.7269

Max Act: 3.5234. Min Act: -0.1700

Data Index: 1104303 (C4 (Web Text))

Max Activating Token Index: 948

Text #17

Max Range: 3.7269. Min Range: -3.7269

Max Act: 3.5391. Min Act: -0.1700

Data Index: 342626 (C4 (Web Text))

Max Activating Token Index: 525

Text #18

Max Range: 3.7269. Min Range: -3.7269

Max Act: 3.5077. Min Act: -0.1700

Data Index: 816509 (C4 (Web Text))

Max Activating Token Index: 459

Text #19

Max Range: 3.7269. Min Range: -3.7269

Max Act: 3.5234. Min Act: -0.1700

Data Index: 1352247 (C4 (Web Text))

Max Activating Token Index: 907