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

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

Neuron 1968 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: 3.8484. Min Range: -3.8484

Max Act: 3.8484. Min Act: -0.1700

Data Index: 1066556 (C4 (Web Text))

Max Activating Token Index: 769

Text #1

Max Range: 3.8484. Min Range: -3.8484

Max Act: 3.8484. Min Act: -0.1700

Data Index: 690070 (C4 (Web Text))

Max Activating Token Index: 940

Text #2

Max Range: 3.8484. Min Range: -3.8484

Max Act: 3.7859. Min Act: -0.1700

Data Index: 329618 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 3.8484. Min Range: -3.8484

Max Act: 3.7233. Min Act: -0.1700

Data Index: 674502 (C4 (Web Text))

Max Activating Token Index: 145

Text #4

Max Range: 3.8484. Min Range: -3.8484

Max Act: 3.7233. Min Act: -0.1700

Data Index: 1312498 (C4 (Web Text))

Max Activating Token Index: 875

Text #5

Max Range: 3.8484. Min Range: -3.8484

Max Act: 3.7546. Min Act: -0.1700

Data Index: 156184 (C4 (Web Text))

Max Activating Token Index: 233

Text #6

Max Range: 3.8484. Min Range: -3.8484

Max Act: 3.6294. Min Act: -0.1700

Data Index: 503005 (C4 (Web Text))

Max Activating Token Index: 904

Text #7

Max Range: 3.8484. Min Range: -3.8484

Max Act: 3.6920. Min Act: -0.1700

Data Index: 231341 (C4 (Web Text))

Max Activating Token Index: 770

Text #8

Max Range: 3.8484. Min Range: -3.8484

Max Act: 3.6920. Min Act: -0.1700

Data Index: 865780 (C4 (Web Text))

Max Activating Token Index: 694

Text #9

Max Range: 3.8484. Min Range: -3.8484

Max Act: 3.6294. Min Act: -0.1700

Data Index: 1163238 (C4 (Web Text))

Max Activating Token Index: 923

Text #10

Max Range: 3.8484. Min Range: -3.8484

Max Act: 3.6294. Min Act: -0.1700

Data Index: 240537 (C4 (Web Text))

Max Activating Token Index: 855

Text #11

Max Range: 3.8484. Min Range: -3.8484

Max Act: 3.5981. Min Act: -0.1700

Data Index: 1315785 (C4 (Web Text))

Max Activating Token Index: 151

Text #12

Max Range: 3.8484. Min Range: -3.8484

Max Act: 3.6607. Min Act: -0.1700

Data Index: 341376 (C4 (Web Text))

Max Activating Token Index: 617

Text #13

Max Range: 3.8484. Min Range: -3.8484

Max Act: 3.5981. Min Act: -0.1700

Data Index: 1053428 (C4 (Web Text))

Max Activating Token Index: 392

Text #14

Max Range: 3.8484. Min Range: -3.8484

Max Act: 3.6607. Min Act: -0.1700

Data Index: 774684 (C4 (Web Text))

Max Activating Token Index: 273

Text #15

Max Range: 3.8484. Min Range: -3.8484

Max Act: 3.5981. Min Act: -0.1700

Data Index: 1163771 (C4 (Web Text))

Max Activating Token Index: 757

Text #16

Max Range: 3.8484. Min Range: -3.8484

Max Act: 3.5981. Min Act: -0.1700

Data Index: 1203266 (C4 (Web Text))

Max Activating Token Index: 678

Text #17

Max Range: 3.8484. Min Range: -3.8484

Max Act: 3.6607. Min Act: -0.1700

Data Index: 533017 (C4 (Web Text))

Max Activating Token Index: 408

Text #18

Max Range: 3.8484. Min Range: -3.8484

Max Act: 3.5981. Min Act: -0.1700

Data Index: 545589 (C4 (Web Text))

Max Activating Token Index: 168

Text #19

Max Range: 3.8484. Min Range: -3.8484

Max Act: 3.5981. Min Act: -0.1699

Data Index: 104337 (C4 (Web Text))

Max Activating Token Index: 570