Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1172 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.3789. Min Range: -5.3789

Max Act: 5.3789. Min Act: -0.1700

Data Index: 308401 (C4 (Web Text))

Max Activating Token Index: 575

Text #1

Max Range: 5.3789. Min Range: -5.3789

Max Act: 5.2226. Min Act: -0.1700

Data Index: 381395 (C4 (Web Text))

Max Activating Token Index: 41

Text #2

Max Range: 5.3789. Min Range: -5.3789

Max Act: 5.2851. Min Act: -0.1700

Data Index: 1280946 (C4 (Web Text))

Max Activating Token Index: 279

Text #3

Max Range: 5.3789. Min Range: -5.3789

Max Act: 5.2851. Min Act: -0.1700

Data Index: 1187589 (C4 (Web Text))

Max Activating Token Index: 462

Text #4

Max Range: 5.3789. Min Range: -5.3789

Max Act: 5.2539. Min Act: -0.1700

Data Index: 16680 (C4 (Web Text))

Max Activating Token Index: 956

Text #5

Max Range: 5.3789. Min Range: -5.3789

Max Act: 5.2226. Min Act: -0.1700

Data Index: 19404 (C4 (Web Text))

Max Activating Token Index: 95

Text #6

Max Range: 5.3789. Min Range: -5.3789

Max Act: 5.2539. Min Act: -0.1700

Data Index: 770929 (C4 (Web Text))

Max Activating Token Index: 166

Text #7

Max Range: 5.3789. Min Range: -5.3789

Max Act: 5.2851. Min Act: -0.1700

Data Index: 898919 (C4 (Web Text))

Max Activating Token Index: 401

Text #8

Max Range: 5.3789. Min Range: -5.3789

Max Act: 5.1914. Min Act: -0.1700

Data Index: 162399 (C4 (Web Text))

Max Activating Token Index: 279

Text #9

Max Range: 5.3789. Min Range: -5.3789

Max Act: 5.1914. Min Act: -0.1700

Data Index: 1260769 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 5.3789. Min Range: -5.3789

Max Act: 5.1601. Min Act: -0.1700

Data Index: 322676 (C4 (Web Text))

Max Activating Token Index: 997

Text #11

Max Range: 5.3789. Min Range: -5.3789

Max Act: 5.1914. Min Act: -0.1700

Data Index: 335068 (C4 (Web Text))

Max Activating Token Index: 37

Text #12

Max Range: 5.3789. Min Range: -5.3789

Max Act: 5.1914. Min Act: -0.1700

Data Index: 738710 (C4 (Web Text))

Max Activating Token Index: 557

Text #13

Max Range: 5.3789. Min Range: -5.3789

Max Act: 5.1914. Min Act: -0.1700

Data Index: 163341 (C4 (Web Text))

Max Activating Token Index: 307

Text #14

Max Range: 5.3789. Min Range: -5.3789

Max Act: 5.1914. Min Act: -0.1700

Data Index: 943595 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 5.3789. Min Range: -5.3789

Max Act: 5.0351. Min Act: -0.1700

Data Index: 99692 (C4 (Web Text))

Max Activating Token Index: 1003

Text #16

Max Range: 5.3789. Min Range: -5.3789

Max Act: 5.1601. Min Act: -0.1700

Data Index: 750541 (C4 (Web Text))

Max Activating Token Index: 49

Text #17

Max Range: 5.3789. Min Range: -5.3789

Max Act: 5.1289. Min Act: -0.1700

Data Index: 720173 (C4 (Web Text))

Max Activating Token Index: 883

Text #18

Max Range: 5.3789. Min Range: -5.3789

Max Act: 5.1601. Min Act: -0.1700

Data Index: 613116 (C4 (Web Text))

Max Activating Token Index: 76

Text #19

Max Range: 5.3789. Min Range: -5.3789

Max Act: 5.1289. Min Act: -0.1700

Data Index: 1236057 (C4 (Web Text))

Max Activating Token Index: 338