Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 59 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.0025. Min Range: -3.0025

Max Act: 3.0025. Min Act: -0.1700

Data Index: 1357745 (C4 (Web Text))

Max Activating Token Index: 181

Text #1

Max Range: 3.0025. Min Range: -3.0025

Max Act: 2.9709. Min Act: -0.1700

Data Index: 606826 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 3.0025. Min Range: -3.0025

Max Act: 2.9075. Min Act: -0.1700

Data Index: 199135 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 3.0025. Min Range: -3.0025

Max Act: 2.8917. Min Act: -0.1700

Data Index: 1278785 (C4 (Web Text))

Max Activating Token Index: 206

Text #4

Max Range: 3.0025. Min Range: -3.0025

Max Act: 2.8758. Min Act: -0.1700

Data Index: 1007187 (C4 (Web Text))

Max Activating Token Index: 735

Text #5

Max Range: 3.0025. Min Range: -3.0025

Max Act: 2.8599. Min Act: -0.1700

Data Index: 250162 (C4 (Web Text))

Max Activating Token Index: 17

Text #6

Max Range: 3.0025. Min Range: -3.0025

Max Act: 2.8599. Min Act: -0.1700

Data Index: 427163 (C4 (Web Text))

Max Activating Token Index: 647

Text #7

Max Range: 3.0025. Min Range: -3.0025

Max Act: 2.8599. Min Act: -0.1700

Data Index: 907051 (C4 (Web Text))

Max Activating Token Index: 805

Text #8

Max Range: 3.0025. Min Range: -3.0025

Max Act: 2.8281. Min Act: -0.1700

Data Index: 1024320 (C4 (Web Text))

Max Activating Token Index: 644

Text #9

Max Range: 3.0025. Min Range: -3.0025

Max Act: 2.7963. Min Act: -0.1700

Data Index: 175736 (C4 (Web Text))

Max Activating Token Index: 189

Text #10

Max Range: 3.0025. Min Range: -3.0025

Max Act: 2.8122. Min Act: -0.1700

Data Index: 235671 (C4 (Web Text))

Max Activating Token Index: 38

Text #11

Max Range: 3.0025. Min Range: -3.0025

Max Act: 2.8122. Min Act: -0.1700

Data Index: 706349 (C4 (Web Text))

Max Activating Token Index: 341

Text #12

Max Range: 3.0025. Min Range: -3.0025

Max Act: 2.8122. Min Act: -0.1700

Data Index: 481135 (C4 (Web Text))

Max Activating Token Index: 876

Text #13

Max Range: 3.0025. Min Range: -3.0025

Max Act: 2.7963. Min Act: -0.1700

Data Index: 644192 (C4 (Web Text))

Max Activating Token Index: 888

Text #14

Max Range: 3.0025. Min Range: -3.0025

Max Act: 2.7803. Min Act: -0.1700

Data Index: 940248 (C4 (Web Text))

Max Activating Token Index: 750

Text #15

Max Range: 3.0025. Min Range: -3.0025

Max Act: 2.7803. Min Act: -0.1700

Data Index: 1161015 (C4 (Web Text))

Max Activating Token Index: 443

Text #16

Max Range: 3.0025. Min Range: -3.0025

Max Act: 2.7644. Min Act: -0.1700

Data Index: 1032034 (C4 (Web Text))

Max Activating Token Index: 383

Text #17

Max Range: 3.0025. Min Range: -3.0025

Max Act: 2.7803. Min Act: -0.1700

Data Index: 412362 (C4 (Web Text))

Max Activating Token Index: 192

Text #18

Max Range: 3.0025. Min Range: -3.0025

Max Act: 2.7644. Min Act: -0.1700

Data Index: 216998 (C4 (Web Text))

Max Activating Token Index: 256

Text #19

Max Range: 3.0025. Min Range: -3.0025

Max Act: 2.7803. Min Act: -0.1700

Data Index: 307138 (C4 (Web Text))

Max Activating Token Index: 177