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

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

Neuron 1247 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.8721. Min Range: -3.8721

Max Act: 3.8721. Min Act: -0.1700

Data Index: 886124 (C4 (Web Text))

Max Activating Token Index: 988

Text #1

Max Range: 3.8721. Min Range: -3.8721

Max Act: 3.8721. Min Act: -0.1700

Data Index: 1338000 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 3.8721. Min Range: -3.8721

Max Act: 3.8721. Min Act: -0.1700

Data Index: 1039000 (C4 (Web Text))

Max Activating Token Index: 410

Text #3

Max Range: 3.8721. Min Range: -3.8721

Max Act: 3.8721. Min Act: -0.1700

Data Index: 988810 (C4 (Web Text))

Max Activating Token Index: 308

Text #4

Max Range: 3.8721. Min Range: -3.8721

Max Act: 3.8096. Min Act: -0.1700

Data Index: 128108 (C4 (Web Text))

Max Activating Token Index: 662

Text #5

Max Range: 3.8721. Min Range: -3.8721

Max Act: 3.8408. Min Act: -0.1700

Data Index: 897714 (C4 (Web Text))

Max Activating Token Index: 91

Text #6

Max Range: 3.8721. Min Range: -3.8721

Max Act: 3.8096. Min Act: -0.1700

Data Index: 1022051 (C4 (Web Text))

Max Activating Token Index: 240

Text #7

Max Range: 3.8721. Min Range: -3.8721

Max Act: 3.8408. Min Act: -0.1700

Data Index: 213889 (C4 (Web Text))

Max Activating Token Index: 623

Text #8

Max Range: 3.8721. Min Range: -3.8721

Max Act: 3.8408. Min Act: -0.1700

Data Index: 809035 (C4 (Web Text))

Max Activating Token Index: 1022

Text #9

Max Range: 3.8721. Min Range: -3.8721

Max Act: 3.8096. Min Act: -0.1700

Data Index: 1163407 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 3.8721. Min Range: -3.8721

Max Act: 3.7783. Min Act: -0.1700

Data Index: 347557 (C4 (Web Text))

Max Activating Token Index: 994

Text #11

Max Range: 3.8721. Min Range: -3.8721

Max Act: 3.8096. Min Act: -0.1700

Data Index: 1217165 (C4 (Web Text))

Max Activating Token Index: 445

Text #12

Max Range: 3.8721. Min Range: -3.8721

Max Act: 3.7783. Min Act: -0.1700

Data Index: 18389 (C4 (Web Text))

Max Activating Token Index: 1009

Text #13

Max Range: 3.8721. Min Range: -3.8721

Max Act: 3.8096. Min Act: -0.1700

Data Index: 162679 (C4 (Web Text))

Max Activating Token Index: 915

Text #14

Max Range: 3.8721. Min Range: -3.8721

Max Act: 3.7470. Min Act: -0.1700

Data Index: 1254603 (C4 (Web Text))

Max Activating Token Index: 806

Text #15

Max Range: 3.8721. Min Range: -3.8721

Max Act: 3.7783. Min Act: -0.1700

Data Index: 188518 (C4 (Web Text))

Max Activating Token Index: 248

Text #16

Max Range: 3.8721. Min Range: -3.8721

Max Act: 3.7783. Min Act: -0.1700

Data Index: 769071 (C4 (Web Text))

Max Activating Token Index: 769

Text #17

Max Range: 3.8721. Min Range: -3.8721

Max Act: 3.7783. Min Act: -0.1700

Data Index: 1227698 (C4 (Web Text))

Max Activating Token Index: 937

Text #18

Max Range: 3.8721. Min Range: -3.8721

Max Act: 3.7470. Min Act: -0.1700

Data Index: 170028 (C4 (Web Text))

Max Activating Token Index: 289

Text #19

Max Range: 3.8721. Min Range: -3.8721

Max Act: 3.7783. Min Act: -0.1700

Data Index: 1191343 (C4 (Web Text))

Max Activating Token Index: 397