Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1587 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.1038. Min Range: -5.1038

Max Act: 5.1038. Min Act: -0.1700

Data Index: 1226373 (C4 (Web Text))

Max Activating Token Index: 865

Text #1

Max Range: 5.1038. Min Range: -5.1038

Max Act: 5.0100. Min Act: -0.1700

Data Index: 1082669 (C4 (Web Text))

Max Activating Token Index: 201

Text #2

Max Range: 5.1038. Min Range: -5.1038

Max Act: 4.9788. Min Act: -0.1699

Data Index: 699470 (C4 (Web Text))

Max Activating Token Index: 450

Text #3

Max Range: 5.1038. Min Range: -5.1038

Max Act: 4.9475. Min Act: -0.1700

Data Index: 551489 (C4 (Web Text))

Max Activating Token Index: 323

Text #4

Max Range: 5.1038. Min Range: -5.1038

Max Act: 4.9788. Min Act: -0.1699

Data Index: 9506 (C4 (Web Text))

Max Activating Token Index: 613

Text #5

Max Range: 5.1038. Min Range: -5.1038

Max Act: 4.9475. Min Act: -0.1700

Data Index: 410041 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 5.1038. Min Range: -5.1038

Max Act: 4.9475. Min Act: -0.1700

Data Index: 1106723 (C4 (Web Text))

Max Activating Token Index: 317

Text #7

Max Range: 5.1038. Min Range: -5.1038

Max Act: 4.9163. Min Act: -0.1700

Data Index: 80999 (C4 (Web Text))

Max Activating Token Index: 207

Text #8

Max Range: 5.1038. Min Range: -5.1038

Max Act: 4.8850. Min Act: -0.1700

Data Index: 878899 (C4 (Web Text))

Max Activating Token Index: 60

Text #9

Max Range: 5.1038. Min Range: -5.1038

Max Act: 4.8225. Min Act: -0.1700

Data Index: 1184732 (C4 (Web Text))

Max Activating Token Index: 344

Text #10

Max Range: 5.1038. Min Range: -5.1038

Max Act: 4.8225. Min Act: -0.1700

Data Index: 231498 (C4 (Web Text))

Max Activating Token Index: 46

Text #11

Max Range: 5.1038. Min Range: -5.1038

Max Act: 4.7913. Min Act: -0.1700

Data Index: 519568 (C4 (Web Text))

Max Activating Token Index: 637

Text #12

Max Range: 5.1038. Min Range: -5.1038

Max Act: 4.7600. Min Act: -0.1700

Data Index: 18385 (C4 (Web Text))

Max Activating Token Index: 895

Text #13

Max Range: 5.1038. Min Range: -5.1038

Max Act: 4.7913. Min Act: -0.1700

Data Index: 415349 (C4 (Web Text))

Max Activating Token Index: 727

Text #14

Max Range: 5.1038. Min Range: -5.1038

Max Act: 4.7913. Min Act: -0.1700

Data Index: 983672 (C4 (Web Text))

Max Activating Token Index: 882

Text #15

Max Range: 5.1038. Min Range: -5.1038

Max Act: 4.7913. Min Act: -0.1700

Data Index: 1164563 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 5.1038. Min Range: -5.1038

Max Act: 4.7287. Min Act: -0.1700

Data Index: 348984 (C4 (Web Text))

Max Activating Token Index: 316

Text #17

Max Range: 5.1038. Min Range: -5.1038

Max Act: 4.7600. Min Act: -0.1700

Data Index: 784200 (C4 (Web Text))

Max Activating Token Index: 937

Text #18

Max Range: 5.1038. Min Range: -5.1038

Max Act: 4.7913. Min Act: -0.1700

Data Index: 1293621 (C4 (Web Text))

Max Activating Token Index: 203

Text #19

Max Range: 5.1038. Min Range: -5.1038

Max Act: 4.7600. Min Act: -0.1699

Data Index: 1336243 (C4 (Web Text))

Max Activating Token Index: 671