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

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

Neuron 327 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4718. Min Range: -5.4718

Max Act: 5.4406. Min Act: -0.1700

Data Index: 547251 (C4 (Web Text))

Max Activating Token Index: 935

Text #1

Max Range: 5.4718. Min Range: -5.4718

Max Act: 5.4718. Min Act: -0.1700

Data Index: 281259 (C4 (Web Text))

Max Activating Token Index: 995

Text #2

Max Range: 5.4718. Min Range: -5.4718

Max Act: 5.4406. Min Act: -0.1699

Data Index: 1268021 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 5.4718. Min Range: -5.4718

Max Act: 5.3781. Min Act: -0.1700

Data Index: 345222 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 5.4718. Min Range: -5.4718

Max Act: 5.4093. Min Act: -0.1699

Data Index: 531734 (C4 (Web Text))

Max Activating Token Index: 907

Text #5

Max Range: 5.4718. Min Range: -5.4718

Max Act: 5.4093. Min Act: -0.1700

Data Index: 124415 (C4 (Web Text))

Max Activating Token Index: 996

Text #6

Max Range: 5.4718. Min Range: -5.4718

Max Act: 5.3781. Min Act: -0.1700

Data Index: 642945 (C4 (Web Text))

Max Activating Token Index: 819

Text #7

Max Range: 5.4718. Min Range: -5.4718

Max Act: 5.3781. Min Act: -0.1700

Data Index: 988158 (C4 (Web Text))

Max Activating Token Index: 99

Text #8

Max Range: 5.4718. Min Range: -5.4718

Max Act: 5.3781. Min Act: -0.1700

Data Index: 600012 (C4 (Web Text))

Max Activating Token Index: 164

Text #9

Max Range: 5.4718. Min Range: -5.4718

Max Act: 5.3468. Min Act: -0.1700

Data Index: 1030698 (C4 (Web Text))

Max Activating Token Index: 140

Text #10

Max Range: 5.4718. Min Range: -5.4718

Max Act: 5.3781. Min Act: -0.1700

Data Index: 251473 (C4 (Web Text))

Max Activating Token Index: 386

Text #11

Max Range: 5.4718. Min Range: -5.4718

Max Act: 5.3156. Min Act: -0.1700

Data Index: 474833 (C4 (Web Text))

Max Activating Token Index: 870

Text #12

Max Range: 5.4718. Min Range: -5.4718

Max Act: 5.3468. Min Act: -0.1700

Data Index: 41112 (C4 (Web Text))

Max Activating Token Index: 143

Text #13

Max Range: 5.4718. Min Range: -5.4718

Max Act: 5.2843. Min Act: -0.1700

Data Index: 578040 (C4 (Web Text))

Max Activating Token Index: 533

Text #14

Max Range: 5.4718. Min Range: -5.4718

Max Act: 5.3156. Min Act: -0.1700

Data Index: 989023 (C4 (Web Text))

Max Activating Token Index: 453

Text #15

Max Range: 5.4718. Min Range: -5.4718

Max Act: 5.2531. Min Act: -0.1700

Data Index: 1127006 (C4 (Web Text))

Max Activating Token Index: 156

Text #16

Max Range: 5.4718. Min Range: -5.4718

Max Act: 5.2531. Min Act: -0.1700

Data Index: 83794 (C4 (Web Text))

Max Activating Token Index: 367

Text #17

Max Range: 5.4718. Min Range: -5.4718

Max Act: 5.2218. Min Act: -0.1700

Data Index: 197862 (C4 (Web Text))

Max Activating Token Index: 770

Text #18

Max Range: 5.4718. Min Range: -5.4718

Max Act: 5.2218. Min Act: -0.1700

Data Index: 1074917 (C4 (Web Text))

Max Activating Token Index: 485

Text #19

Max Range: 5.4718. Min Range: -5.4718

Max Act: 5.2218. Min Act: -0.1700

Data Index: 471457 (C4 (Web Text))

Max Activating Token Index: 773