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

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

Neuron 1853 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: 5.9201. Min Range: -5.9201

Max Act: 5.9201. Min Act: -0.1700

Data Index: 933976 (C4 (Web Text))

Max Activating Token Index: 529

Text #1

Max Range: 5.9201. Min Range: -5.9201

Max Act: 5.6701. Min Act: -0.1700

Data Index: 569113 (C4 (Web Text))

Max Activating Token Index: 826

Text #2

Max Range: 5.9201. Min Range: -5.9201

Max Act: 5.7013. Min Act: -0.1700

Data Index: 878898 (C4 (Web Text))

Max Activating Token Index: 211

Text #3

Max Range: 5.9201. Min Range: -5.9201

Max Act: 5.5763. Min Act: -0.1700

Data Index: 1134566 (C4 (Web Text))

Max Activating Token Index: 441

Text #4

Max Range: 5.9201. Min Range: -5.9201

Max Act: 5.5763. Min Act: -0.1700

Data Index: 741469 (C4 (Web Text))

Max Activating Token Index: 794

Text #5

Max Range: 5.9201. Min Range: -5.9201

Max Act: 5.5138. Min Act: -0.1700

Data Index: 1231423 (C4 (Web Text))

Max Activating Token Index: 101

Text #6

Max Range: 5.9201. Min Range: -5.9201

Max Act: 5.5763. Min Act: -0.1700

Data Index: 314849 (C4 (Web Text))

Max Activating Token Index: 833

Text #7

Max Range: 5.9201. Min Range: -5.9201

Max Act: 5.5138. Min Act: -0.1700

Data Index: 1210498 (C4 (Web Text))

Max Activating Token Index: 569

Text #8

Max Range: 5.9201. Min Range: -5.9201

Max Act: 5.5138. Min Act: -0.1700

Data Index: 541339 (C4 (Web Text))

Max Activating Token Index: 405

Text #9

Max Range: 5.9201. Min Range: -5.9201

Max Act: 5.3888. Min Act: -0.1700

Data Index: 304425 (C4 (Web Text))

Max Activating Token Index: 875

Text #10

Max Range: 5.9201. Min Range: -5.9201

Max Act: 5.4513. Min Act: -0.1700

Data Index: 542639 (C4 (Web Text))

Max Activating Token Index: 267

Text #11

Max Range: 5.9201. Min Range: -5.9201

Max Act: 5.4513. Min Act: -0.1700

Data Index: 941526 (C4 (Web Text))

Max Activating Token Index: 432

Text #12

Max Range: 5.9201. Min Range: -5.9201

Max Act: 5.4201. Min Act: -0.1700

Data Index: 350559 (C4 (Web Text))

Max Activating Token Index: 344

Text #13

Max Range: 5.9201. Min Range: -5.9201

Max Act: 5.4513. Min Act: -0.1700

Data Index: 194060 (C4 (Web Text))

Max Activating Token Index: 381

Text #14

Max Range: 5.9201. Min Range: -5.9201

Max Act: 5.3888. Min Act: -0.1700

Data Index: 821784 (C4 (Web Text))

Max Activating Token Index: 359

Text #15

Max Range: 5.9201. Min Range: -5.9201

Max Act: 5.3263. Min Act: -0.1700

Data Index: 545201 (C4 (Web Text))

Max Activating Token Index: 192

Text #16

Max Range: 5.9201. Min Range: -5.9201

Max Act: 5.3263. Min Act: -0.1700

Data Index: 405711 (C4 (Web Text))

Max Activating Token Index: 636

Text #17

Max Range: 5.9201. Min Range: -5.9201

Max Act: 5.3263. Min Act: -0.1700

Data Index: 222079 (C4 (Web Text))

Max Activating Token Index: 861

Text #18

Max Range: 5.9201. Min Range: -5.9201

Max Act: 5.2638. Min Act: -0.1700

Data Index: 845044 (C4 (Web Text))

Max Activating Token Index: 102

Text #19

Max Range: 5.9201. Min Range: -5.9201

Max Act: 5.3263. Min Act: -0.1700

Data Index: 1037939 (C4 (Web Text))

Max Activating Token Index: 664