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

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

Neuron 276 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: 3.7098. Min Range: -3.7098

Max Act: 3.7098. Min Act: -0.1700

Data Index: 1468203 (Python Code)

Max Activating Token Index: 20

Text #1

Max Range: 3.7098. Min Range: -3.7098

Max Act: 3.6629. Min Act: -0.1700

Data Index: 1004092 (C4 (Web Text))

Max Activating Token Index: 221

Text #2

Max Range: 3.7098. Min Range: -3.7098

Max Act: 3.6159. Min Act: -0.1700

Data Index: 143280 (C4 (Web Text))

Max Activating Token Index: 443

Text #3

Max Range: 3.7098. Min Range: -3.7098

Max Act: 3.6159. Min Act: -0.1700

Data Index: 1126598 (C4 (Web Text))

Max Activating Token Index: 281

Text #4

Max Range: 3.7098. Min Range: -3.7098

Max Act: 3.6316. Min Act: -0.1700

Data Index: 66248 (C4 (Web Text))

Max Activating Token Index: 582

Text #5

Max Range: 3.7098. Min Range: -3.7098

Max Act: 3.6159. Min Act: -0.1700

Data Index: 107839 (C4 (Web Text))

Max Activating Token Index: 986

Text #6

Max Range: 3.7098. Min Range: -3.7098

Max Act: 3.6316. Min Act: -0.1700

Data Index: 1230181 (C4 (Web Text))

Max Activating Token Index: 622

Text #7

Max Range: 3.7098. Min Range: -3.7098

Max Act: 3.6316. Min Act: -0.1700

Data Index: 807931 (C4 (Web Text))

Max Activating Token Index: 124

Text #8

Max Range: 3.7098. Min Range: -3.7098

Max Act: 3.5220. Min Act: -0.1700

Data Index: 706238 (C4 (Web Text))

Max Activating Token Index: 498

Text #9

Max Range: 3.7098. Min Range: -3.7098

Max Act: 3.5689. Min Act: -0.1700

Data Index: 1166404 (C4 (Web Text))

Max Activating Token Index: 829

Text #10

Max Range: 3.7098. Min Range: -3.7098

Max Act: 3.5063. Min Act: -0.1700

Data Index: 1066910 (C4 (Web Text))

Max Activating Token Index: 149

Text #11

Max Range: 3.7098. Min Range: -3.7098

Max Act: 3.5846. Min Act: -0.1700

Data Index: 165408 (C4 (Web Text))

Max Activating Token Index: 346

Text #12

Max Range: 3.7098. Min Range: -3.7098

Max Act: 3.5533. Min Act: -0.1699

Data Index: 798015 (C4 (Web Text))

Max Activating Token Index: 799

Text #13

Max Range: 3.7098. Min Range: -3.7098

Max Act: 3.5533. Min Act: -0.1700

Data Index: 835647 (C4 (Web Text))

Max Activating Token Index: 539

Text #14

Max Range: 3.7098. Min Range: -3.7098

Max Act: 3.5376. Min Act: -0.1700

Data Index: 679895 (C4 (Web Text))

Max Activating Token Index: 268

Text #15

Max Range: 3.7098. Min Range: -3.7098

Max Act: 3.5689. Min Act: -0.1700

Data Index: 383479 (C4 (Web Text))

Max Activating Token Index: 494

Text #16

Max Range: 3.7098. Min Range: -3.7098

Max Act: 3.6316. Min Act: -0.1700

Data Index: 1343515 (C4 (Web Text))

Max Activating Token Index: 612

Text #17

Max Range: 3.7098. Min Range: -3.7098

Max Act: 3.5376. Min Act: -0.1700

Data Index: 1464916 (Python Code)

Max Activating Token Index: 19

Text #18

Max Range: 3.7098. Min Range: -3.7098

Max Act: 3.5220. Min Act: -0.1700

Data Index: 668295 (C4 (Web Text))

Max Activating Token Index: 129

Text #19

Max Range: 3.7098. Min Range: -3.7098

Max Act: 3.5063. Min Act: -0.1700

Data Index: 669921 (C4 (Web Text))

Max Activating Token Index: 369