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

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

Neuron 1025 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: 5.0513. Min Range: -5.0513

Max Act: 5.0513. Min Act: -0.1700

Data Index: 595285 (C4 (Web Text))

Max Activating Token Index: 833

Text #1

Max Range: 5.0513. Min Range: -5.0513

Max Act: 5.0201. Min Act: -0.1700

Data Index: 424971 (C4 (Web Text))

Max Activating Token Index: 1013

Text #2

Max Range: 5.0513. Min Range: -5.0513

Max Act: 4.8326. Min Act: -0.1700

Data Index: 811698 (C4 (Web Text))

Max Activating Token Index: 974

Text #3

Max Range: 5.0513. Min Range: -5.0513

Max Act: 4.8638. Min Act: -0.1700

Data Index: 1163721 (C4 (Web Text))

Max Activating Token Index: 697

Text #4

Max Range: 5.0513. Min Range: -5.0513

Max Act: 4.8326. Min Act: -0.1700

Data Index: 194130 (C4 (Web Text))

Max Activating Token Index: 863

Text #5

Max Range: 5.0513. Min Range: -5.0513

Max Act: 4.7701. Min Act: -0.1700

Data Index: 1045887 (C4 (Web Text))

Max Activating Token Index: 725

Text #6

Max Range: 5.0513. Min Range: -5.0513

Max Act: 4.7388. Min Act: -0.1700

Data Index: 814022 (C4 (Web Text))

Max Activating Token Index: 384

Text #7

Max Range: 5.0513. Min Range: -5.0513

Max Act: 4.8013. Min Act: -0.1700

Data Index: 376546 (C4 (Web Text))

Max Activating Token Index: 863

Text #8

Max Range: 5.0513. Min Range: -5.0513

Max Act: 4.6763. Min Act: -0.1700

Data Index: 1198607 (C4 (Web Text))

Max Activating Token Index: 644

Text #9

Max Range: 5.0513. Min Range: -5.0513

Max Act: 4.7076. Min Act: -0.1700

Data Index: 809462 (C4 (Web Text))

Max Activating Token Index: 704

Text #10

Max Range: 5.0513. Min Range: -5.0513

Max Act: 4.6763. Min Act: -0.1700

Data Index: 733000 (C4 (Web Text))

Max Activating Token Index: 337

Text #11

Max Range: 5.0513. Min Range: -5.0513

Max Act: 4.7388. Min Act: -0.1700

Data Index: 1256924 (C4 (Web Text))

Max Activating Token Index: 943

Text #12

Max Range: 5.0513. Min Range: -5.0513

Max Act: 4.7388. Min Act: -0.1700

Data Index: 168201 (C4 (Web Text))

Max Activating Token Index: 769

Text #13

Max Range: 5.0513. Min Range: -5.0513

Max Act: 4.7076. Min Act: -0.1700

Data Index: 567955 (C4 (Web Text))

Max Activating Token Index: 753

Text #14

Max Range: 5.0513. Min Range: -5.0513

Max Act: 4.6451. Min Act: -0.1700

Data Index: 324639 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 5.0513. Min Range: -5.0513

Max Act: 4.6451. Min Act: -0.1699

Data Index: 1257927 (C4 (Web Text))

Max Activating Token Index: 772

Text #16

Max Range: 5.0513. Min Range: -5.0513

Max Act: 4.5826. Min Act: -0.1700

Data Index: 488946 (C4 (Web Text))

Max Activating Token Index: 903

Text #17

Max Range: 5.0513. Min Range: -5.0513

Max Act: 4.5826. Min Act: -0.1700

Data Index: 1230173 (C4 (Web Text))

Max Activating Token Index: 858

Text #18

Max Range: 5.0513. Min Range: -5.0513

Max Act: 4.6138. Min Act: -0.1700

Data Index: 500943 (C4 (Web Text))

Max Activating Token Index: 866

Text #19

Max Range: 5.0513. Min Range: -5.0513

Max Act: 4.6138. Min Act: -0.1700

Data Index: 56985 (C4 (Web Text))

Max Activating Token Index: 685