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

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

Neuron 1753 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: 5.6034. Min Range: -5.6034

Max Act: 5.6034. Min Act: -0.1700

Data Index: 958042 (C4 (Web Text))

Max Activating Token Index: 1017

Text #1

Max Range: 5.6034. Min Range: -5.6034

Max Act: 5.3534. Min Act: -0.1700

Data Index: 686515 (C4 (Web Text))

Max Activating Token Index: 268

Text #2

Max Range: 5.6034. Min Range: -5.6034

Max Act: 5.2596. Min Act: -0.1700

Data Index: 312426 (C4 (Web Text))

Max Activating Token Index: 68

Text #3

Max Range: 5.6034. Min Range: -5.6034

Max Act: 5.2909. Min Act: -0.1700

Data Index: 318543 (C4 (Web Text))

Max Activating Token Index: 334

Text #4

Max Range: 5.6034. Min Range: -5.6034

Max Act: 5.2596. Min Act: -0.1699

Data Index: 1298426 (C4 (Web Text))

Max Activating Token Index: 1000

Text #5

Max Range: 5.6034. Min Range: -5.6034

Max Act: 5.2596. Min Act: -0.1700

Data Index: 284633 (C4 (Web Text))

Max Activating Token Index: 604

Text #6

Max Range: 5.6034. Min Range: -5.6034

Max Act: 5.1346. Min Act: -0.1700

Data Index: 485473 (C4 (Web Text))

Max Activating Token Index: 922

Text #7

Max Range: 5.6034. Min Range: -5.6034

Max Act: 5.1659. Min Act: -0.1699

Data Index: 1226401 (C4 (Web Text))

Max Activating Token Index: 255

Text #8

Max Range: 5.6034. Min Range: -5.6034

Max Act: 5.1971. Min Act: -0.1699

Data Index: 936558 (C4 (Web Text))

Max Activating Token Index: 408

Text #9

Max Range: 5.6034. Min Range: -5.6034

Max Act: 5.1971. Min Act: -0.1699

Data Index: 849236 (C4 (Web Text))

Max Activating Token Index: 978

Text #10

Max Range: 5.6034. Min Range: -5.6034

Max Act: 5.1346. Min Act: -0.1699

Data Index: 287270 (C4 (Web Text))

Max Activating Token Index: 319

Text #11

Max Range: 5.6034. Min Range: -5.6034

Max Act: 5.1346. Min Act: -0.1700

Data Index: 1262244 (C4 (Web Text))

Max Activating Token Index: 195

Text #12

Max Range: 5.6034. Min Range: -5.6034

Max Act: 5.0409. Min Act: -0.1700

Data Index: 708095 (C4 (Web Text))

Max Activating Token Index: 850

Text #13

Max Range: 5.6034. Min Range: -5.6034

Max Act: 5.0096. Min Act: -0.1700

Data Index: 5944 (C4 (Web Text))

Max Activating Token Index: 807

Text #14

Max Range: 5.6034. Min Range: -5.6034

Max Act: 5.0096. Min Act: -0.1700

Data Index: 1246825 (C4 (Web Text))

Max Activating Token Index: 850

Text #15

Max Range: 5.6034. Min Range: -5.6034

Max Act: 5.1034. Min Act: -0.1700

Data Index: 1034608 (C4 (Web Text))

Max Activating Token Index: 1018

Text #16

Max Range: 5.6034. Min Range: -5.6034

Max Act: 5.1659. Min Act: -0.1700

Data Index: 658903 (C4 (Web Text))

Max Activating Token Index: 182

Text #17

Max Range: 5.6034. Min Range: -5.6034

Max Act: 5.0409. Min Act: -0.1700

Data Index: 228091 (C4 (Web Text))

Max Activating Token Index: 80

Text #18

Max Range: 5.6034. Min Range: -5.6034

Max Act: 5.0721. Min Act: -0.1700

Data Index: 150708 (C4 (Web Text))

Max Activating Token Index: 583

Text #19

Max Range: 5.6034. Min Range: -5.6034

Max Act: 5.1346. Min Act: -0.1696

Data Index: 1218965 (C4 (Web Text))

Max Activating Token Index: 164