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

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

Neuron 385 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: 5.2403. Min Range: -5.2403

Max Act: 5.2403. Min Act: -0.1700

Data Index: 233189 (C4 (Web Text))

Max Activating Token Index: 106

Text #1

Max Range: 5.2403. Min Range: -5.2403

Max Act: 5.1778. Min Act: -0.1700

Data Index: 1071407 (C4 (Web Text))

Max Activating Token Index: 990

Text #2

Max Range: 5.2403. Min Range: -5.2403

Max Act: 5.1153. Min Act: -0.1700

Data Index: 916865 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 5.2403. Min Range: -5.2403

Max Act: 5.0528. Min Act: -0.1699

Data Index: 1291730 (C4 (Web Text))

Max Activating Token Index: 259

Text #4

Max Range: 5.2403. Min Range: -5.2403

Max Act: 5.0215. Min Act: -0.1700

Data Index: 462535 (C4 (Web Text))

Max Activating Token Index: 791

Text #5

Max Range: 5.2403. Min Range: -5.2403

Max Act: 5.0528. Min Act: -0.1700

Data Index: 61585 (C4 (Web Text))

Max Activating Token Index: 29

Text #6

Max Range: 5.2403. Min Range: -5.2403

Max Act: 5.0528. Min Act: -0.1700

Data Index: 912718 (C4 (Web Text))

Max Activating Token Index: 458

Text #7

Max Range: 5.2403. Min Range: -5.2403

Max Act: 5.0528. Min Act: -0.1700

Data Index: 729205 (C4 (Web Text))

Max Activating Token Index: 686

Text #8

Max Range: 5.2403. Min Range: -5.2403

Max Act: 5.0215. Min Act: -0.1700

Data Index: 740558 (C4 (Web Text))

Max Activating Token Index: 66

Text #9

Max Range: 5.2403. Min Range: -5.2403

Max Act: 4.9590. Min Act: -0.1700

Data Index: 189440 (C4 (Web Text))

Max Activating Token Index: 650

Text #10

Max Range: 5.2403. Min Range: -5.2403

Max Act: 4.9903. Min Act: -0.1700

Data Index: 119396 (C4 (Web Text))

Max Activating Token Index: 163

Text #11

Max Range: 5.2403. Min Range: -5.2403

Max Act: 4.9590. Min Act: -0.1700

Data Index: 519519 (C4 (Web Text))

Max Activating Token Index: 1018

Text #12

Max Range: 5.2403. Min Range: -5.2403

Max Act: 4.9903. Min Act: -0.1700

Data Index: 1124842 (C4 (Web Text))

Max Activating Token Index: 367

Text #13

Max Range: 5.2403. Min Range: -5.2403

Max Act: 4.9590. Min Act: -0.1700

Data Index: 721406 (C4 (Web Text))

Max Activating Token Index: 408

Text #14

Max Range: 5.2403. Min Range: -5.2403

Max Act: 4.9903. Min Act: -0.1699

Data Index: 1150290 (C4 (Web Text))

Max Activating Token Index: 454

Text #15

Max Range: 5.2403. Min Range: -5.2403

Max Act: 4.8965. Min Act: -0.1700

Data Index: 567618 (C4 (Web Text))

Max Activating Token Index: 757

Text #16

Max Range: 5.2403. Min Range: -5.2403

Max Act: 4.9590. Min Act: -0.1700

Data Index: 1065058 (C4 (Web Text))

Max Activating Token Index: 41

Text #17

Max Range: 5.2403. Min Range: -5.2403

Max Act: 4.8965. Min Act: -0.1700

Data Index: 871817 (C4 (Web Text))

Max Activating Token Index: 641

Text #18

Max Range: 5.2403. Min Range: -5.2403

Max Act: 4.9278. Min Act: -0.1695

Data Index: 644156 (C4 (Web Text))

Max Activating Token Index: 931

Text #19

Max Range: 5.2403. Min Range: -5.2403

Max Act: 4.8965. Min Act: -0.1700

Data Index: 26823 (C4 (Web Text))

Max Activating Token Index: 366