Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1770 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 7.9707. Min Range: -7.9707

Max Act: 7.9707. Min Act: -0.1699

Data Index: 573496 (C4 (Web Text))

Max Activating Token Index: 407

Text #1

Max Range: 7.9707. Min Range: -7.9707

Max Act: 7.7207. Min Act: -0.1700

Data Index: 346234 (C4 (Web Text))

Max Activating Token Index: 587

Text #2

Max Range: 7.9707. Min Range: -7.9707

Max Act: 7.4707. Min Act: -0.1700

Data Index: 1223765 (C4 (Web Text))

Max Activating Token Index: 585

Text #3

Max Range: 7.9707. Min Range: -7.9707

Max Act: 7.5332. Min Act: -0.1700

Data Index: 539003 (C4 (Web Text))

Max Activating Token Index: 773

Text #4

Max Range: 7.9707. Min Range: -7.9707

Max Act: 7.4082. Min Act: -0.1698

Data Index: 164949 (C4 (Web Text))

Max Activating Token Index: 753

Text #5

Max Range: 7.9707. Min Range: -7.9707

Max Act: 7.4082. Min Act: -0.1700

Data Index: 285552 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 7.9707. Min Range: -7.9707

Max Act: 7.4082. Min Act: -0.1699

Data Index: 977936 (C4 (Web Text))

Max Activating Token Index: 450

Text #7

Max Range: 7.9707. Min Range: -7.9707

Max Act: 7.2832. Min Act: -0.1700

Data Index: 263519 (C4 (Web Text))

Max Activating Token Index: 927

Text #8

Max Range: 7.9707. Min Range: -7.9707

Max Act: 7.3457. Min Act: -0.1699

Data Index: 1264869 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 7.9707. Min Range: -7.9707

Max Act: 7.3457. Min Act: -0.1700

Data Index: 148682 (C4 (Web Text))

Max Activating Token Index: 773

Text #10

Max Range: 7.9707. Min Range: -7.9707

Max Act: 7.2832. Min Act: -0.1698

Data Index: 1180039 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 7.9707. Min Range: -7.9707

Max Act: 7.2207. Min Act: -0.1700

Data Index: 46892 (C4 (Web Text))

Max Activating Token Index: 768

Text #12

Max Range: 7.9707. Min Range: -7.9707

Max Act: 7.2832. Min Act: -0.1700

Data Index: 549249 (C4 (Web Text))

Max Activating Token Index: 485

Text #13

Max Range: 7.9707. Min Range: -7.9707

Max Act: 7.2832. Min Act: -0.1700

Data Index: 252253 (C4 (Web Text))

Max Activating Token Index: 725

Text #14

Max Range: 7.9707. Min Range: -7.9707

Max Act: 7.2207. Min Act: -0.1700

Data Index: 185306 (C4 (Web Text))

Max Activating Token Index: 311

Text #15

Max Range: 7.9707. Min Range: -7.9707

Max Act: 7.0332. Min Act: -0.1699

Data Index: 1116007 (C4 (Web Text))

Max Activating Token Index: 557

Text #16

Max Range: 7.9707. Min Range: -7.9707

Max Act: 7.0957. Min Act: -0.1700

Data Index: 1198521 (C4 (Web Text))

Max Activating Token Index: 329

Text #17

Max Range: 7.9707. Min Range: -7.9707

Max Act: 7.0957. Min Act: -0.1700

Data Index: 866619 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 7.9707. Min Range: -7.9707

Max Act: 7.0332. Min Act: -0.1700

Data Index: 730190 (C4 (Web Text))

Max Activating Token Index: 807

Text #19

Max Range: 7.9707. Min Range: -7.9707

Max Act: 7.1582. Min Act: -0.1700

Data Index: 630005 (C4 (Web Text))

Max Activating Token Index: 834