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

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

Neuron 656 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: 3.9655. Min Range: -3.9655

Max Act: 3.9655. Min Act: -0.1700

Data Index: 527496 (C4 (Web Text))

Max Activating Token Index: 38

Text #1

Max Range: 3.9655. Min Range: -3.9655

Max Act: 3.9029. Min Act: -0.1700

Data Index: 185580 (C4 (Web Text))

Max Activating Token Index: 602

Text #2

Max Range: 3.9655. Min Range: -3.9655

Max Act: 3.8404. Min Act: -0.1700

Data Index: 378752 (C4 (Web Text))

Max Activating Token Index: 646

Text #3

Max Range: 3.9655. Min Range: -3.9655

Max Act: 3.7778. Min Act: -0.1700

Data Index: 188212 (C4 (Web Text))

Max Activating Token Index: 648

Text #4

Max Range: 3.9655. Min Range: -3.9655

Max Act: 3.8091. Min Act: -0.1700

Data Index: 371071 (C4 (Web Text))

Max Activating Token Index: 339

Text #5

Max Range: 3.9655. Min Range: -3.9655

Max Act: 3.7465. Min Act: -0.1700

Data Index: 346432 (C4 (Web Text))

Max Activating Token Index: 416

Text #6

Max Range: 3.9655. Min Range: -3.9655

Max Act: 3.6840. Min Act: -0.1700

Data Index: 186626 (C4 (Web Text))

Max Activating Token Index: 957

Text #7

Max Range: 3.9655. Min Range: -3.9655

Max Act: 3.7465. Min Act: -0.1700

Data Index: 1252548 (C4 (Web Text))

Max Activating Token Index: 222

Text #8

Max Range: 3.9655. Min Range: -3.9655

Max Act: 3.7778. Min Act: -0.1700

Data Index: 389477 (C4 (Web Text))

Max Activating Token Index: 510

Text #9

Max Range: 3.9655. Min Range: -3.9655

Max Act: 3.7153. Min Act: -0.1700

Data Index: 1039055 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 3.9655. Min Range: -3.9655

Max Act: 3.7778. Min Act: -0.1700

Data Index: 11144 (C4 (Web Text))

Max Activating Token Index: 596

Text #11

Max Range: 3.9655. Min Range: -3.9655

Max Act: 3.6840. Min Act: -0.1700

Data Index: 626032 (C4 (Web Text))

Max Activating Token Index: 941

Text #12

Max Range: 3.9655. Min Range: -3.9655

Max Act: 3.6527. Min Act: -0.1700

Data Index: 1000665 (C4 (Web Text))

Max Activating Token Index: 705

Text #13

Max Range: 3.9655. Min Range: -3.9655

Max Act: 3.6527. Min Act: -0.1700

Data Index: 141991 (C4 (Web Text))

Max Activating Token Index: 757

Text #14

Max Range: 3.9655. Min Range: -3.9655

Max Act: 3.6214. Min Act: -0.1700

Data Index: 1073476 (C4 (Web Text))

Max Activating Token Index: 588

Text #15

Max Range: 3.9655. Min Range: -3.9655

Max Act: 3.6527. Min Act: -0.1700

Data Index: 1040254 (C4 (Web Text))

Max Activating Token Index: 1001

Text #16

Max Range: 3.9655. Min Range: -3.9655

Max Act: 3.5900. Min Act: -0.1700

Data Index: 1253091 (C4 (Web Text))

Max Activating Token Index: 842

Text #17

Max Range: 3.9655. Min Range: -3.9655

Max Act: 3.6214. Min Act: -0.1700

Data Index: 1310846 (C4 (Web Text))

Max Activating Token Index: 559

Text #18

Max Range: 3.9655. Min Range: -3.9655

Max Act: 3.6214. Min Act: -0.1700

Data Index: 130490 (C4 (Web Text))

Max Activating Token Index: 916

Text #19

Max Range: 3.9655. Min Range: -3.9655

Max Act: 3.6214. Min Act: -0.1700

Data Index: 936093 (C4 (Web Text))

Max Activating Token Index: 483