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

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

Neuron 1511 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6665. Min Range: -5.6665

Max Act: 5.6665. Min Act: -0.1700

Data Index: 1170428 (C4 (Web Text))

Max Activating Token Index: 147

Text #1

Max Range: 5.6665. Min Range: -5.6665

Max Act: 5.5728. Min Act: -0.1700

Data Index: 181389 (C4 (Web Text))

Max Activating Token Index: 312

Text #2

Max Range: 5.6665. Min Range: -5.6665

Max Act: 5.4165. Min Act: -0.1700

Data Index: 17333 (C4 (Web Text))

Max Activating Token Index: 717

Text #3

Max Range: 5.6665. Min Range: -5.6665

Max Act: 5.4478. Min Act: -0.1700

Data Index: 293967 (C4 (Web Text))

Max Activating Token Index: 153

Text #4

Max Range: 5.6665. Min Range: -5.6665

Max Act: 5.4165. Min Act: -0.1700

Data Index: 264604 (C4 (Web Text))

Max Activating Token Index: 210

Text #5

Max Range: 5.6665. Min Range: -5.6665

Max Act: 5.4165. Min Act: -0.1700

Data Index: 781604 (C4 (Web Text))

Max Activating Token Index: 702

Text #6

Max Range: 5.6665. Min Range: -5.6665

Max Act: 5.4478. Min Act: -0.1700

Data Index: 413238 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 5.6665. Min Range: -5.6665

Max Act: 5.4165. Min Act: -0.1700

Data Index: 474552 (C4 (Web Text))

Max Activating Token Index: 192

Text #8

Max Range: 5.6665. Min Range: -5.6665

Max Act: 5.4165. Min Act: -0.1700

Data Index: 1141543 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 5.6665. Min Range: -5.6665

Max Act: 5.3540. Min Act: -0.1700

Data Index: 308913 (C4 (Web Text))

Max Activating Token Index: 869

Text #10

Max Range: 5.6665. Min Range: -5.6665

Max Act: 5.3540. Min Act: -0.1700

Data Index: 1119258 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 5.6665. Min Range: -5.6665

Max Act: 5.3228. Min Act: -0.1700

Data Index: 836960 (C4 (Web Text))

Max Activating Token Index: 658

Text #12

Max Range: 5.6665. Min Range: -5.6665

Max Act: 5.3540. Min Act: -0.1700

Data Index: 28262 (C4 (Web Text))

Max Activating Token Index: 672

Text #13

Max Range: 5.6665. Min Range: -5.6665

Max Act: 5.3228. Min Act: -0.1700

Data Index: 129887 (C4 (Web Text))

Max Activating Token Index: 20

Text #14

Max Range: 5.6665. Min Range: -5.6665

Max Act: 5.3540. Min Act: -0.1700

Data Index: 986385 (C4 (Web Text))

Max Activating Token Index: 992

Text #15

Max Range: 5.6665. Min Range: -5.6665

Max Act: 5.3228. Min Act: -0.1700

Data Index: 215151 (C4 (Web Text))

Max Activating Token Index: 439

Text #16

Max Range: 5.6665. Min Range: -5.6665

Max Act: 5.3540. Min Act: -0.1700

Data Index: 21854 (C4 (Web Text))

Max Activating Token Index: 259

Text #17

Max Range: 5.6665. Min Range: -5.6665

Max Act: 5.2603. Min Act: -0.1700

Data Index: 825497 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 5.6665. Min Range: -5.6665

Max Act: 5.2603. Min Act: -0.1700

Data Index: 626797 (C4 (Web Text))

Max Activating Token Index: 767

Text #19

Max Range: 5.6665. Min Range: -5.6665

Max Act: 5.2915. Min Act: -0.1700

Data Index: 855132 (C4 (Web Text))

Max Activating Token Index: 843