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

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

Neuron 825 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: 3.3804. Min Range: -3.3804

Max Act: 3.3804. Min Act: -0.1700

Data Index: 1045365 (C4 (Web Text))

Max Activating Token Index: 1011

Text #1

Max Range: 3.3804. Min Range: -3.3804

Max Act: 3.2705. Min Act: -0.1700

Data Index: 25590 (C4 (Web Text))

Max Activating Token Index: 858

Text #2

Max Range: 3.3804. Min Range: -3.3804

Max Act: 3.1132. Min Act: -0.1700

Data Index: 1014966 (C4 (Web Text))

Max Activating Token Index: 706

Text #3

Max Range: 3.3804. Min Range: -3.3804

Max Act: 3.0816. Min Act: -0.1700

Data Index: 1261221 (C4 (Web Text))

Max Activating Token Index: 340

Text #4

Max Range: 3.3804. Min Range: -3.3804

Max Act: 3.1132. Min Act: -0.1700

Data Index: 719419 (C4 (Web Text))

Max Activating Token Index: 978

Text #5

Max Range: 3.3804. Min Range: -3.3804

Max Act: 3.1132. Min Act: -0.1700

Data Index: 940989 (C4 (Web Text))

Max Activating Token Index: 940

Text #6

Max Range: 3.3804. Min Range: -3.3804

Max Act: 3.0816. Min Act: -0.1700

Data Index: 258386 (C4 (Web Text))

Max Activating Token Index: 872

Text #7

Max Range: 3.3804. Min Range: -3.3804

Max Act: 3.0501. Min Act: -0.1700

Data Index: 24014 (C4 (Web Text))

Max Activating Token Index: 658

Text #8

Max Range: 3.3804. Min Range: -3.3804

Max Act: 3.0658. Min Act: -0.1700

Data Index: 1339983 (C4 (Web Text))

Max Activating Token Index: 994

Text #9

Max Range: 3.3804. Min Range: -3.3804

Max Act: 2.9394. Min Act: -0.1700

Data Index: 1220964 (C4 (Web Text))

Max Activating Token Index: 473

Text #10

Max Range: 3.3804. Min Range: -3.3804

Max Act: 3.0343. Min Act: -0.1700

Data Index: 1032371 (C4 (Web Text))

Max Activating Token Index: 743

Text #11

Max Range: 3.3804. Min Range: -3.3804

Max Act: 3.0343. Min Act: -0.1700

Data Index: 1038311 (C4 (Web Text))

Max Activating Token Index: 581

Text #12

Max Range: 3.3804. Min Range: -3.3804

Max Act: 3.0658. Min Act: -0.1700

Data Index: 189081 (C4 (Web Text))

Max Activating Token Index: 830

Text #13

Max Range: 3.3804. Min Range: -3.3804

Max Act: 3.0658. Min Act: -0.1700

Data Index: 1094144 (C4 (Web Text))

Max Activating Token Index: 256

Text #14

Max Range: 3.3804. Min Range: -3.3804

Max Act: 3.0343. Min Act: -0.1700

Data Index: 58752 (C4 (Web Text))

Max Activating Token Index: 759

Text #15

Max Range: 3.3804. Min Range: -3.3804

Max Act: 3.0185. Min Act: -0.1700

Data Index: 184552 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 3.3804. Min Range: -3.3804

Max Act: 3.0185. Min Act: -0.1700

Data Index: 659657 (C4 (Web Text))

Max Activating Token Index: 356

Text #17

Max Range: 3.3804. Min Range: -3.3804

Max Act: 3.0185. Min Act: -0.1700

Data Index: 311797 (C4 (Web Text))

Max Activating Token Index: 669

Text #18

Max Range: 3.3804. Min Range: -3.3804

Max Act: 2.9869. Min Act: -0.1700

Data Index: 129313 (C4 (Web Text))

Max Activating Token Index: 691

Text #19

Max Range: 3.3804. Min Range: -3.3804

Max Act: 3.0185. Min Act: -0.1700

Data Index: 1246666 (C4 (Web Text))

Max Activating Token Index: 185