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

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

Neuron 1004 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: 5.9921. Min Range: -5.9921

Max Act: 5.9921. Min Act: -0.1700

Data Index: 1006696 (C4 (Web Text))

Max Activating Token Index: 317

Text #1

Max Range: 5.9921. Min Range: -5.9921

Max Act: 5.8358. Min Act: -0.1699

Data Index: 848142 (C4 (Web Text))

Max Activating Token Index: 404

Text #2

Max Range: 5.9921. Min Range: -5.9921

Max Act: 5.6796. Min Act: -0.1700

Data Index: 206299 (C4 (Web Text))

Max Activating Token Index: 858

Text #3

Max Range: 5.9921. Min Range: -5.9921

Max Act: 5.6796. Min Act: -0.1700

Data Index: 1300553 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 5.9921. Min Range: -5.9921

Max Act: 5.6483. Min Act: -0.1700

Data Index: 406200 (C4 (Web Text))

Max Activating Token Index: 437

Text #5

Max Range: 5.9921. Min Range: -5.9921

Max Act: 5.5858. Min Act: -0.1700

Data Index: 1084654 (C4 (Web Text))

Max Activating Token Index: 789

Text #6

Max Range: 5.9921. Min Range: -5.9921

Max Act: 5.6171. Min Act: -0.1700

Data Index: 811886 (C4 (Web Text))

Max Activating Token Index: 863

Text #7

Max Range: 5.9921. Min Range: -5.9921

Max Act: 5.5858. Min Act: -0.1700

Data Index: 616658 (C4 (Web Text))

Max Activating Token Index: 1018

Text #8

Max Range: 5.9921. Min Range: -5.9921

Max Act: 5.5546. Min Act: -0.1700

Data Index: 1338386 (C4 (Web Text))

Max Activating Token Index: 456

Text #9

Max Range: 5.9921. Min Range: -5.9921

Max Act: 5.5858. Min Act: -0.1700

Data Index: 749594 (C4 (Web Text))

Max Activating Token Index: 176

Text #10

Max Range: 5.9921. Min Range: -5.9921

Max Act: 5.5858. Min Act: -0.1700

Data Index: 773643 (C4 (Web Text))

Max Activating Token Index: 508

Text #11

Max Range: 5.9921. Min Range: -5.9921

Max Act: 5.6171. Min Act: -0.1700

Data Index: 1059557 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 5.9921. Min Range: -5.9921

Max Act: 5.6171. Min Act: -0.1700

Data Index: 853179 (C4 (Web Text))

Max Activating Token Index: 430

Text #13

Max Range: 5.9921. Min Range: -5.9921

Max Act: 5.5546. Min Act: -0.1700

Data Index: 1016218 (C4 (Web Text))

Max Activating Token Index: 354

Text #14

Max Range: 5.9921. Min Range: -5.9921

Max Act: 5.5546. Min Act: -0.1700

Data Index: 782267 (C4 (Web Text))

Max Activating Token Index: 973

Text #15

Max Range: 5.9921. Min Range: -5.9921

Max Act: 5.5546. Min Act: -0.1700

Data Index: 782043 (C4 (Web Text))

Max Activating Token Index: 604

Text #16

Max Range: 5.9921. Min Range: -5.9921

Max Act: 5.5546. Min Act: -0.1700

Data Index: 554073 (C4 (Web Text))

Max Activating Token Index: 643

Text #17

Max Range: 5.9921. Min Range: -5.9921

Max Act: 5.5233. Min Act: -0.1700

Data Index: 877501 (C4 (Web Text))

Max Activating Token Index: 179

Text #18

Max Range: 5.9921. Min Range: -5.9921

Max Act: 5.4921. Min Act: -0.1700

Data Index: 883916 (C4 (Web Text))

Max Activating Token Index: 601

Text #19

Max Range: 5.9921. Min Range: -5.9921

Max Act: 5.5233. Min Act: -0.1700

Data Index: 340365 (C4 (Web Text))

Max Activating Token Index: 708