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

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

Neuron 1832 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.6847. Min Act: -0.1700

Data Index: 1164129 (C4 (Web Text))

Max Activating Token Index: 694

Text #1

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.6534. Min Act: -0.1700

Data Index: 1269710 (C4 (Web Text))

Max Activating Token Index: 810

Text #2

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.6690. Min Act: -0.1700

Data Index: 721782 (C4 (Web Text))

Max Activating Token Index: 401

Text #3

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.6377. Min Act: -0.1700

Data Index: 583635 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.6220. Min Act: -0.1700

Data Index: 135244 (C4 (Web Text))

Max Activating Token Index: 28

Text #5

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.5751. Min Act: -0.1700

Data Index: 1132241 (C4 (Web Text))

Max Activating Token Index: 859

Text #6

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.5751. Min Act: -0.1700

Data Index: 1196069 (C4 (Web Text))

Max Activating Token Index: 346

Text #7

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.5281. Min Act: -0.1700

Data Index: 1093942 (C4 (Web Text))

Max Activating Token Index: 177

Text #8

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.5594. Min Act: -0.1700

Data Index: 1241478 (C4 (Web Text))

Max Activating Token Index: 734

Text #9

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.5751. Min Act: -0.1700

Data Index: 306809 (C4 (Web Text))

Max Activating Token Index: 637

Text #10

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.5438. Min Act: -0.1700

Data Index: 1257236 (C4 (Web Text))

Max Activating Token Index: 541

Text #11

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.5281. Min Act: -0.1700

Data Index: 1076274 (C4 (Web Text))

Max Activating Token Index: 27

Text #12

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.5281. Min Act: -0.1700

Data Index: 434175 (C4 (Web Text))

Max Activating Token Index: 910

Text #13

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.5124. Min Act: -0.1700

Data Index: 1260021 (C4 (Web Text))

Max Activating Token Index: 419

Text #14

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.5281. Min Act: -0.1700

Data Index: 1041523 (C4 (Web Text))

Max Activating Token Index: 256

Text #15

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.5281. Min Act: -0.1700

Data Index: 1220877 (C4 (Web Text))

Max Activating Token Index: 687

Text #16

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.5281. Min Act: -0.1700

Data Index: 766499 (C4 (Web Text))

Max Activating Token Index: 594

Text #17

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.5281. Min Act: -0.1700

Data Index: 1324685 (C4 (Web Text))

Max Activating Token Index: 742

Text #18

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.5124. Min Act: -0.1700

Data Index: 337834 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.4968. Min Act: -0.1700

Data Index: 380858 (C4 (Web Text))

Max Activating Token Index: 270