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

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

Neuron 1297 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: 7.4379. Min Range: -7.4379

Max Act: 7.4379. Min Act: -0.1700

Data Index: 263323 (C4 (Web Text))

Max Activating Token Index: 223

Text #1

Max Range: 7.4379. Min Range: -7.4379

Max Act: 7.1566. Min Act: -0.1700

Data Index: 55742 (C4 (Web Text))

Max Activating Token Index: 120

Text #2

Max Range: 7.4379. Min Range: -7.4379

Max Act: 7.1566. Min Act: -0.1700

Data Index: 847647 (C4 (Web Text))

Max Activating Token Index: 987

Text #3

Max Range: 7.4379. Min Range: -7.4379

Max Act: 7.1566. Min Act: -0.1700

Data Index: 158581 (C4 (Web Text))

Max Activating Token Index: 127

Text #4

Max Range: 7.4379. Min Range: -7.4379

Max Act: 7.0629. Min Act: -0.1700

Data Index: 139855 (C4 (Web Text))

Max Activating Token Index: 790

Text #5

Max Range: 7.4379. Min Range: -7.4379

Max Act: 7.0941. Min Act: -0.1700

Data Index: 24576 (C4 (Web Text))

Max Activating Token Index: 542

Text #6

Max Range: 7.4379. Min Range: -7.4379

Max Act: 6.8754. Min Act: -0.1700

Data Index: 108579 (C4 (Web Text))

Max Activating Token Index: 273

Text #7

Max Range: 7.4379. Min Range: -7.4379

Max Act: 6.8754. Min Act: -0.1700

Data Index: 1092598 (C4 (Web Text))

Max Activating Token Index: 801

Text #8

Max Range: 7.4379. Min Range: -7.4379

Max Act: 6.9691. Min Act: -0.1700

Data Index: 676555 (C4 (Web Text))

Max Activating Token Index: 312

Text #9

Max Range: 7.4379. Min Range: -7.4379

Max Act: 6.8754. Min Act: -0.1700

Data Index: 788304 (C4 (Web Text))

Max Activating Token Index: 540

Text #10

Max Range: 7.4379. Min Range: -7.4379

Max Act: 6.8441. Min Act: -0.1698

Data Index: 1159095 (C4 (Web Text))

Max Activating Token Index: 589

Text #11

Max Range: 7.4379. Min Range: -7.4379

Max Act: 6.8441. Min Act: -0.1700

Data Index: 746755 (C4 (Web Text))

Max Activating Token Index: 180

Text #12

Max Range: 7.4379. Min Range: -7.4379

Max Act: 6.7504. Min Act: -0.1700

Data Index: 1012624 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 7.4379. Min Range: -7.4379

Max Act: 6.7504. Min Act: -0.1700

Data Index: 852970 (C4 (Web Text))

Max Activating Token Index: 461

Text #14

Max Range: 7.4379. Min Range: -7.4379

Max Act: 6.7504. Min Act: -0.1699

Data Index: 842960 (C4 (Web Text))

Max Activating Token Index: 1011

Text #15

Max Range: 7.4379. Min Range: -7.4379

Max Act: 6.8441. Min Act: -0.1700

Data Index: 1263362 (C4 (Web Text))

Max Activating Token Index: 610

Text #16

Max Range: 7.4379. Min Range: -7.4379

Max Act: 6.7816. Min Act: -0.1700

Data Index: 673198 (C4 (Web Text))

Max Activating Token Index: 465

Text #17

Max Range: 7.4379. Min Range: -7.4379

Max Act: 6.7504. Min Act: -0.1699

Data Index: 738451 (C4 (Web Text))

Max Activating Token Index: 716

Text #18

Max Range: 7.4379. Min Range: -7.4379

Max Act: 6.7816. Min Act: -0.1700

Data Index: 274357 (C4 (Web Text))

Max Activating Token Index: 878

Text #19

Max Range: 7.4379. Min Range: -7.4379

Max Act: 6.6879. Min Act: -0.1700

Data Index: 963651 (C4 (Web Text))

Max Activating Token Index: 947