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

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

Neuron 1396 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: 3.6920. Min Range: -3.6920

Max Act: 3.6920. Min Act: -0.1700

Data Index: 640490 (C4 (Web Text))

Max Activating Token Index: 776

Text #1

Max Range: 3.6920. Min Range: -3.6920

Max Act: 3.6294. Min Act: -0.1700

Data Index: 885185 (C4 (Web Text))

Max Activating Token Index: 735

Text #2

Max Range: 3.6920. Min Range: -3.6920

Max Act: 3.6294. Min Act: -0.1700

Data Index: 854040 (C4 (Web Text))

Max Activating Token Index: 763

Text #3

Max Range: 3.6920. Min Range: -3.6920

Max Act: 3.5981. Min Act: -0.1700

Data Index: 1014164 (C4 (Web Text))

Max Activating Token Index: 830

Text #4

Max Range: 3.6920. Min Range: -3.6920

Max Act: 3.6294. Min Act: -0.1700

Data Index: 209901 (C4 (Web Text))

Max Activating Token Index: 829

Text #5

Max Range: 3.6920. Min Range: -3.6920

Max Act: 3.5668. Min Act: -0.1700

Data Index: 617868 (C4 (Web Text))

Max Activating Token Index: 869

Text #6

Max Range: 3.6920. Min Range: -3.6920

Max Act: 3.5981. Min Act: -0.1700

Data Index: 537513 (C4 (Web Text))

Max Activating Token Index: 839

Text #7

Max Range: 3.6920. Min Range: -3.6920

Max Act: 3.5668. Min Act: -0.1700

Data Index: 798564 (C4 (Web Text))

Max Activating Token Index: 455

Text #8

Max Range: 3.6920. Min Range: -3.6920

Max Act: 3.5981. Min Act: -0.1700

Data Index: 509253 (C4 (Web Text))

Max Activating Token Index: 605

Text #9

Max Range: 3.6920. Min Range: -3.6920

Max Act: 3.5668. Min Act: -0.1700

Data Index: 5881 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 3.6920. Min Range: -3.6920

Max Act: 3.5355. Min Act: -0.1700

Data Index: 357012 (C4 (Web Text))

Max Activating Token Index: 710

Text #11

Max Range: 3.6920. Min Range: -3.6920

Max Act: 3.5355. Min Act: -0.1700

Data Index: 948016 (C4 (Web Text))

Max Activating Token Index: 81

Text #12

Max Range: 3.6920. Min Range: -3.6920

Max Act: 3.5355. Min Act: -0.1700

Data Index: 300773 (C4 (Web Text))

Max Activating Token Index: 825

Text #13

Max Range: 3.6920. Min Range: -3.6920

Max Act: 3.5041. Min Act: -0.1700

Data Index: 120402 (C4 (Web Text))

Max Activating Token Index: 652

Text #14

Max Range: 3.6920. Min Range: -3.6920

Max Act: 3.5041. Min Act: -0.1700

Data Index: 6869 (C4 (Web Text))

Max Activating Token Index: 812

Text #15

Max Range: 3.6920. Min Range: -3.6920

Max Act: 3.5355. Min Act: -0.1700

Data Index: 152226 (C4 (Web Text))

Max Activating Token Index: 852

Text #16

Max Range: 3.6920. Min Range: -3.6920

Max Act: 3.5041. Min Act: -0.1700

Data Index: 1235210 (C4 (Web Text))

Max Activating Token Index: 808

Text #17

Max Range: 3.6920. Min Range: -3.6920

Max Act: 3.4728. Min Act: -0.1700

Data Index: 240387 (C4 (Web Text))

Max Activating Token Index: 699

Text #18

Max Range: 3.6920. Min Range: -3.6920

Max Act: 3.5041. Min Act: -0.1700

Data Index: 242075 (C4 (Web Text))

Max Activating Token Index: 296

Text #19

Max Range: 3.6920. Min Range: -3.6920

Max Act: 3.5041. Min Act: -0.1700

Data Index: 982941 (C4 (Web Text))

Max Activating Token Index: 77