Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1419 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.9891. Min Range: -3.9891

Max Act: 3.9891. Min Act: -0.1699

Data Index: 292471 (C4 (Web Text))

Max Activating Token Index: 753

Text #1

Max Range: 3.9891. Min Range: -3.9891

Max Act: 3.8640. Min Act: -0.1700

Data Index: 334389 (C4 (Web Text))

Max Activating Token Index: 82

Text #2

Max Range: 3.9891. Min Range: -3.9891

Max Act: 3.8328. Min Act: -0.1700

Data Index: 1107149 (C4 (Web Text))

Max Activating Token Index: 155

Text #3

Max Range: 3.9891. Min Range: -3.9891

Max Act: 3.8328. Min Act: -0.1700

Data Index: 1035535 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 3.9891. Min Range: -3.9891

Max Act: 3.7858. Min Act: -0.1700

Data Index: 632931 (C4 (Web Text))

Max Activating Token Index: 768

Text #5

Max Range: 3.9891. Min Range: -3.9891

Max Act: 3.8328. Min Act: -0.1700

Data Index: 276275 (C4 (Web Text))

Max Activating Token Index: 268

Text #6

Max Range: 3.9891. Min Range: -3.9891

Max Act: 3.7389. Min Act: -0.1700

Data Index: 197364 (C4 (Web Text))

Max Activating Token Index: 286

Text #7

Max Range: 3.9891. Min Range: -3.9891

Max Act: 3.7546. Min Act: -0.1700

Data Index: 1114369 (C4 (Web Text))

Max Activating Token Index: 1018

Text #8

Max Range: 3.9891. Min Range: -3.9891

Max Act: 3.7858. Min Act: -0.1700

Data Index: 938225 (C4 (Web Text))

Max Activating Token Index: 767

Text #9

Max Range: 3.9891. Min Range: -3.9891

Max Act: 3.7858. Min Act: -0.1699

Data Index: 1065136 (C4 (Web Text))

Max Activating Token Index: 518

Text #10

Max Range: 3.9891. Min Range: -3.9891

Max Act: 3.7702. Min Act: -0.1699

Data Index: 792642 (C4 (Web Text))

Max Activating Token Index: 662

Text #11

Max Range: 3.9891. Min Range: -3.9891

Max Act: 3.7858. Min Act: -0.1699

Data Index: 532280 (C4 (Web Text))

Max Activating Token Index: 576

Text #12

Max Range: 3.9891. Min Range: -3.9891

Max Act: 3.7858. Min Act: -0.1700

Data Index: 157699 (C4 (Web Text))

Max Activating Token Index: 406

Text #13

Max Range: 3.9891. Min Range: -3.9891

Max Act: 3.7546. Min Act: -0.1700

Data Index: 1122494 (C4 (Web Text))

Max Activating Token Index: 614

Text #14

Max Range: 3.9891. Min Range: -3.9891

Max Act: 3.7546. Min Act: -0.1700

Data Index: 1215379 (C4 (Web Text))

Max Activating Token Index: 187

Text #15

Max Range: 3.9891. Min Range: -3.9891

Max Act: 3.7233. Min Act: -0.1700

Data Index: 508534 (C4 (Web Text))

Max Activating Token Index: 273

Text #16

Max Range: 3.9891. Min Range: -3.9891

Max Act: 3.7546. Min Act: -0.1700

Data Index: 590553 (C4 (Web Text))

Max Activating Token Index: 633

Text #17

Max Range: 3.9891. Min Range: -3.9891

Max Act: 3.7233. Min Act: -0.1700

Data Index: 106909 (C4 (Web Text))

Max Activating Token Index: 233

Text #18

Max Range: 3.9891. Min Range: -3.9891

Max Act: 3.7389. Min Act: -0.1700

Data Index: 1188349 (C4 (Web Text))

Max Activating Token Index: 31

Text #19

Max Range: 3.9891. Min Range: -3.9891

Max Act: 3.7389. Min Act: -0.1699

Data Index: 641921 (C4 (Web Text))

Max Activating Token Index: 791