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

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

Neuron 1358 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6761. Min Range: -3.6761

Max Act: 3.6761. Min Act: -0.1700

Data Index: 101320 (C4 (Web Text))

Max Activating Token Index: 1020

Text #1

Max Range: 3.6761. Min Range: -3.6761

Max Act: 3.5821. Min Act: -0.1700

Data Index: 989192 (C4 (Web Text))

Max Activating Token Index: 421

Text #2

Max Range: 3.6761. Min Range: -3.6761

Max Act: 3.5508. Min Act: -0.1700

Data Index: 1047600 (C4 (Web Text))

Max Activating Token Index: 360

Text #3

Max Range: 3.6761. Min Range: -3.6761

Max Act: 3.5508. Min Act: -0.1700

Data Index: 391252 (C4 (Web Text))

Max Activating Token Index: 733

Text #4

Max Range: 3.6761. Min Range: -3.6761

Max Act: 3.4881. Min Act: -0.1700

Data Index: 1154043 (C4 (Web Text))

Max Activating Token Index: 891

Text #5

Max Range: 3.6761. Min Range: -3.6761

Max Act: 3.4881. Min Act: -0.1700

Data Index: 126968 (C4 (Web Text))

Max Activating Token Index: 863

Text #6

Max Range: 3.6761. Min Range: -3.6761

Max Act: 3.5195. Min Act: -0.1700

Data Index: 654170 (C4 (Web Text))

Max Activating Token Index: 223

Text #7

Max Range: 3.6761. Min Range: -3.6761

Max Act: 3.5195. Min Act: -0.1700

Data Index: 702845 (C4 (Web Text))

Max Activating Token Index: 94

Text #8

Max Range: 3.6761. Min Range: -3.6761

Max Act: 3.5195. Min Act: -0.1700

Data Index: 687754 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 3.6761. Min Range: -3.6761

Max Act: 3.5195. Min Act: -0.1700

Data Index: 686392 (C4 (Web Text))

Max Activating Token Index: 499

Text #10

Max Range: 3.6761. Min Range: -3.6761

Max Act: 3.4725. Min Act: -0.1700

Data Index: 738923 (C4 (Web Text))

Max Activating Token Index: 273

Text #11

Max Range: 3.6761. Min Range: -3.6761

Max Act: 3.4881. Min Act: -0.1700

Data Index: 932877 (C4 (Web Text))

Max Activating Token Index: 181

Text #12

Max Range: 3.6761. Min Range: -3.6761

Max Act: 3.4881. Min Act: -0.1700

Data Index: 825461 (C4 (Web Text))

Max Activating Token Index: 1004

Text #13

Max Range: 3.6761. Min Range: -3.6761

Max Act: 3.4881. Min Act: -0.1700

Data Index: 487159 (C4 (Web Text))

Max Activating Token Index: 849

Text #14

Max Range: 3.6761. Min Range: -3.6761

Max Act: 3.4881. Min Act: -0.1700

Data Index: 383747 (C4 (Web Text))

Max Activating Token Index: 382

Text #15

Max Range: 3.6761. Min Range: -3.6761

Max Act: 3.4881. Min Act: -0.1700

Data Index: 164387 (C4 (Web Text))

Max Activating Token Index: 359

Text #16

Max Range: 3.6761. Min Range: -3.6761

Max Act: 3.4568. Min Act: -0.1700

Data Index: 419267 (C4 (Web Text))

Max Activating Token Index: 96

Text #17

Max Range: 3.6761. Min Range: -3.6761

Max Act: 3.4568. Min Act: -0.1700

Data Index: 1002491 (C4 (Web Text))

Max Activating Token Index: 473

Text #18

Max Range: 3.6761. Min Range: -3.6761

Max Act: 3.4568. Min Act: -0.1700

Data Index: 406282 (C4 (Web Text))

Max Activating Token Index: 1015

Text #19

Max Range: 3.6761. Min Range: -3.6761

Max Act: 3.4411. Min Act: -0.1700

Data Index: 1123429 (C4 (Web Text))

Max Activating Token Index: 907