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

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

Neuron 410 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: 5.6411. Min Range: -5.6411

Max Act: 5.6411. Min Act: -0.1700

Data Index: 664039 (C4 (Web Text))

Max Activating Token Index: 486

Text #1

Max Range: 5.6411. Min Range: -5.6411

Max Act: 5.4536. Min Act: -0.1700

Data Index: 853365 (C4 (Web Text))

Max Activating Token Index: 188

Text #2

Max Range: 5.6411. Min Range: -5.6411

Max Act: 5.3911. Min Act: -0.1700

Data Index: 481029 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 5.6411. Min Range: -5.6411

Max Act: 5.4849. Min Act: -0.1700

Data Index: 1072841 (C4 (Web Text))

Max Activating Token Index: 497

Text #4

Max Range: 5.6411. Min Range: -5.6411

Max Act: 5.4224. Min Act: -0.1700

Data Index: 73449 (C4 (Web Text))

Max Activating Token Index: 663

Text #5

Max Range: 5.6411. Min Range: -5.6411

Max Act: 5.4536. Min Act: -0.1700

Data Index: 377714 (C4 (Web Text))

Max Activating Token Index: 847

Text #6

Max Range: 5.6411. Min Range: -5.6411

Max Act: 5.2974. Min Act: -0.1700

Data Index: 718373 (C4 (Web Text))

Max Activating Token Index: 225

Text #7

Max Range: 5.6411. Min Range: -5.6411

Max Act: 5.2349. Min Act: -0.1700

Data Index: 1340033 (C4 (Web Text))

Max Activating Token Index: 241

Text #8

Max Range: 5.6411. Min Range: -5.6411

Max Act: 5.2036. Min Act: -0.1700

Data Index: 267980 (C4 (Web Text))

Max Activating Token Index: 253

Text #9

Max Range: 5.6411. Min Range: -5.6411

Max Act: 5.1411. Min Act: -0.1700

Data Index: 874536 (C4 (Web Text))

Max Activating Token Index: 379

Text #10

Max Range: 5.6411. Min Range: -5.6411

Max Act: 5.1411. Min Act: -0.1700

Data Index: 425969 (C4 (Web Text))

Max Activating Token Index: 191

Text #11

Max Range: 5.6411. Min Range: -5.6411

Max Act: 5.1724. Min Act: -0.1700

Data Index: 1002697 (C4 (Web Text))

Max Activating Token Index: 513

Text #12

Max Range: 5.6411. Min Range: -5.6411

Max Act: 5.1099. Min Act: -0.1700

Data Index: 556716 (C4 (Web Text))

Max Activating Token Index: 586

Text #13

Max Range: 5.6411. Min Range: -5.6411

Max Act: 5.1099. Min Act: -0.1700

Data Index: 648088 (C4 (Web Text))

Max Activating Token Index: 593

Text #14

Max Range: 5.6411. Min Range: -5.6411

Max Act: 5.1099. Min Act: -0.1700

Data Index: 997426 (C4 (Web Text))

Max Activating Token Index: 658

Text #15

Max Range: 5.6411. Min Range: -5.6411

Max Act: 5.0786. Min Act: -0.1700

Data Index: 725760 (C4 (Web Text))

Max Activating Token Index: 703

Text #16

Max Range: 5.6411. Min Range: -5.6411

Max Act: 5.0786. Min Act: -0.1700

Data Index: 91340 (C4 (Web Text))

Max Activating Token Index: 831

Text #17

Max Range: 5.6411. Min Range: -5.6411

Max Act: 5.0786. Min Act: -0.1700

Data Index: 22913 (C4 (Web Text))

Max Activating Token Index: 180

Text #18

Max Range: 5.6411. Min Range: -5.6411

Max Act: 4.9849. Min Act: -0.1700

Data Index: 308366 (C4 (Web Text))

Max Activating Token Index: 295

Text #19

Max Range: 5.6411. Min Range: -5.6411

Max Act: 5.0161. Min Act: -0.1700

Data Index: 208023 (C4 (Web Text))

Max Activating Token Index: 809