Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1267 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.3755. Min Range: -3.3755

Max Act: 3.3755. Min Act: -0.1700

Data Index: 114396 (C4 (Web Text))

Max Activating Token Index: 235

Text #1

Max Range: 3.3755. Min Range: -3.3755

Max Act: 3.3284. Min Act: -0.1700

Data Index: 1155133 (C4 (Web Text))

Max Activating Token Index: 218

Text #2

Max Range: 3.3755. Min Range: -3.3755

Max Act: 3.2813. Min Act: -0.1700

Data Index: 89234 (C4 (Web Text))

Max Activating Token Index: 383

Text #3

Max Range: 3.3755. Min Range: -3.3755

Max Act: 3.2342. Min Act: -0.1700

Data Index: 396869 (C4 (Web Text))

Max Activating Token Index: 786

Text #4

Max Range: 3.3755. Min Range: -3.3755

Max Act: 3.1398. Min Act: -0.1700

Data Index: 1356228 (C4 (Web Text))

Max Activating Token Index: 206

Text #5

Max Range: 3.3755. Min Range: -3.3755

Max Act: 3.1555. Min Act: -0.1700

Data Index: 956543 (C4 (Web Text))

Max Activating Token Index: 949

Text #6

Max Range: 3.3755. Min Range: -3.3755

Max Act: 3.1240. Min Act: -0.1700

Data Index: 1095481 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 3.3755. Min Range: -3.3755

Max Act: 3.1082. Min Act: -0.1700

Data Index: 1318571 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 3.3755. Min Range: -3.3755

Max Act: 3.0925. Min Act: -0.1700

Data Index: 319369 (C4 (Web Text))

Max Activating Token Index: 912

Text #9

Max Range: 3.3755. Min Range: -3.3755

Max Act: 3.1082. Min Act: -0.1700

Data Index: 191359 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 3.3755. Min Range: -3.3755

Max Act: 3.1082. Min Act: -0.1700

Data Index: 782740 (C4 (Web Text))

Max Activating Token Index: 236

Text #11

Max Range: 3.3755. Min Range: -3.3755

Max Act: 3.0609. Min Act: -0.1700

Data Index: 927026 (C4 (Web Text))

Max Activating Token Index: 899

Text #12

Max Range: 3.3755. Min Range: -3.3755

Max Act: 3.0925. Min Act: -0.1700

Data Index: 990538 (C4 (Web Text))

Max Activating Token Index: 287

Text #13

Max Range: 3.3755. Min Range: -3.3755

Max Act: 3.0767. Min Act: -0.1700

Data Index: 78781 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 3.3755. Min Range: -3.3755

Max Act: 3.1082. Min Act: -0.1700

Data Index: 1323374 (C4 (Web Text))

Max Activating Token Index: 96

Text #15

Max Range: 3.3755. Min Range: -3.3755

Max Act: 3.0609. Min Act: -0.1700

Data Index: 593065 (C4 (Web Text))

Max Activating Token Index: 155

Text #16

Max Range: 3.3755. Min Range: -3.3755

Max Act: 3.0609. Min Act: -0.1700

Data Index: 238299 (C4 (Web Text))

Max Activating Token Index: 946

Text #17

Max Range: 3.3755. Min Range: -3.3755

Max Act: 3.0609. Min Act: -0.1700

Data Index: 1008645 (C4 (Web Text))

Max Activating Token Index: 249

Text #18

Max Range: 3.3755. Min Range: -3.3755

Max Act: 3.0925. Min Act: -0.1700

Data Index: 859670 (C4 (Web Text))

Max Activating Token Index: 595

Text #19

Max Range: 3.3755. Min Range: -3.3755

Max Act: 3.0767. Min Act: -0.1700

Data Index: 15783 (C4 (Web Text))

Max Activating Token Index: 896