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

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

Neuron 1037 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.1686. Min Range: -6.1686

Max Act: 6.1373. Min Act: -0.1700

Data Index: 1079392 (C4 (Web Text))

Max Activating Token Index: 233

Text #1

Max Range: 6.1686. Min Range: -6.1686

Max Act: 6.1686. Min Act: -0.1700

Data Index: 539469 (C4 (Web Text))

Max Activating Token Index: 438

Text #2

Max Range: 6.1686. Min Range: -6.1686

Max Act: 6.1061. Min Act: -0.1700

Data Index: 268121 (C4 (Web Text))

Max Activating Token Index: 978

Text #3

Max Range: 6.1686. Min Range: -6.1686

Max Act: 6.0748. Min Act: -0.1700

Data Index: 142020 (C4 (Web Text))

Max Activating Token Index: 343

Text #4

Max Range: 6.1686. Min Range: -6.1686

Max Act: 6.0123. Min Act: -0.1700

Data Index: 143546 (C4 (Web Text))

Max Activating Token Index: 416

Text #5

Max Range: 6.1686. Min Range: -6.1686

Max Act: 6.0436. Min Act: -0.1700

Data Index: 934889 (C4 (Web Text))

Max Activating Token Index: 342

Text #6

Max Range: 6.1686. Min Range: -6.1686

Max Act: 5.9811. Min Act: -0.1700

Data Index: 563810 (C4 (Web Text))

Max Activating Token Index: 417

Text #7

Max Range: 6.1686. Min Range: -6.1686

Max Act: 5.9498. Min Act: -0.1700

Data Index: 319051 (C4 (Web Text))

Max Activating Token Index: 222

Text #8

Max Range: 6.1686. Min Range: -6.1686

Max Act: 5.9186. Min Act: -0.1700

Data Index: 990939 (C4 (Web Text))

Max Activating Token Index: 994

Text #9

Max Range: 6.1686. Min Range: -6.1686

Max Act: 5.9186. Min Act: -0.1700

Data Index: 849932 (C4 (Web Text))

Max Activating Token Index: 351

Text #10

Max Range: 6.1686. Min Range: -6.1686

Max Act: 5.9186. Min Act: -0.1700

Data Index: 1143408 (C4 (Web Text))

Max Activating Token Index: 480

Text #11

Max Range: 6.1686. Min Range: -6.1686

Max Act: 5.8561. Min Act: -0.1700

Data Index: 311633 (C4 (Web Text))

Max Activating Token Index: 477

Text #12

Max Range: 6.1686. Min Range: -6.1686

Max Act: 5.8873. Min Act: -0.1700

Data Index: 756062 (C4 (Web Text))

Max Activating Token Index: 89

Text #13

Max Range: 6.1686. Min Range: -6.1686

Max Act: 5.7623. Min Act: -0.1700

Data Index: 1357035 (C4 (Web Text))

Max Activating Token Index: 784

Text #14

Max Range: 6.1686. Min Range: -6.1686

Max Act: 5.8873. Min Act: -0.1700

Data Index: 1340889 (C4 (Web Text))

Max Activating Token Index: 508

Text #15

Max Range: 6.1686. Min Range: -6.1686

Max Act: 5.8873. Min Act: -0.1700

Data Index: 187068 (C4 (Web Text))

Max Activating Token Index: 427

Text #16

Max Range: 6.1686. Min Range: -6.1686

Max Act: 5.7936. Min Act: -0.1700

Data Index: 167243 (C4 (Web Text))

Max Activating Token Index: 401

Text #17

Max Range: 6.1686. Min Range: -6.1686

Max Act: 5.7936. Min Act: -0.1700

Data Index: 617442 (C4 (Web Text))

Max Activating Token Index: 785

Text #18

Max Range: 6.1686. Min Range: -6.1686

Max Act: 5.7936. Min Act: -0.1700

Data Index: 1268760 (C4 (Web Text))

Max Activating Token Index: 1019

Text #19

Max Range: 6.1686. Min Range: -6.1686

Max Act: 5.8248. Min Act: -0.1700

Data Index: 1308418 (C4 (Web Text))

Max Activating Token Index: 217