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

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

Neuron 1123 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: 7.0852. Min Range: -7.0852

Max Act: 7.0852. Min Act: -0.1700

Data Index: 274998 (C4 (Web Text))

Max Activating Token Index: 753

Text #1

Max Range: 7.0852. Min Range: -7.0852

Max Act: 6.3352. Min Act: -0.1700

Data Index: 329065 (C4 (Web Text))

Max Activating Token Index: 825

Text #2

Max Range: 7.0852. Min Range: -7.0852

Max Act: 6.3352. Min Act: -0.1700

Data Index: 506798 (C4 (Web Text))

Max Activating Token Index: 668

Text #3

Max Range: 7.0852. Min Range: -7.0852

Max Act: 6.2727. Min Act: -0.1700

Data Index: 304271 (C4 (Web Text))

Max Activating Token Index: 455

Text #4

Max Range: 7.0852. Min Range: -7.0852

Max Act: 6.1789. Min Act: -0.1700

Data Index: 178136 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 7.0852. Min Range: -7.0852

Max Act: 6.1789. Min Act: -0.1700

Data Index: 102479 (C4 (Web Text))

Max Activating Token Index: 848

Text #6

Max Range: 7.0852. Min Range: -7.0852

Max Act: 6.1477. Min Act: -0.1700

Data Index: 136774 (C4 (Web Text))

Max Activating Token Index: 387

Text #7

Max Range: 7.0852. Min Range: -7.0852

Max Act: 6.1164. Min Act: -0.1700

Data Index: 1020212 (C4 (Web Text))

Max Activating Token Index: 626

Text #8

Max Range: 7.0852. Min Range: -7.0852

Max Act: 6.1789. Min Act: -0.1700

Data Index: 1235112 (C4 (Web Text))

Max Activating Token Index: 511

Text #9

Max Range: 7.0852. Min Range: -7.0852

Max Act: 6.0539. Min Act: -0.1700

Data Index: 543719 (C4 (Web Text))

Max Activating Token Index: 323

Text #10

Max Range: 7.0852. Min Range: -7.0852

Max Act: 6.0539. Min Act: -0.1700

Data Index: 891978 (C4 (Web Text))

Max Activating Token Index: 991

Text #11

Max Range: 7.0852. Min Range: -7.0852

Max Act: 6.0227. Min Act: -0.1700

Data Index: 1270974 (C4 (Web Text))

Max Activating Token Index: 641

Text #12

Max Range: 7.0852. Min Range: -7.0852

Max Act: 5.9914. Min Act: -0.1700

Data Index: 537401 (C4 (Web Text))

Max Activating Token Index: 929

Text #13

Max Range: 7.0852. Min Range: -7.0852

Max Act: 5.9914. Min Act: -0.1700

Data Index: 407814 (C4 (Web Text))

Max Activating Token Index: 244

Text #14

Max Range: 7.0852. Min Range: -7.0852

Max Act: 5.9602. Min Act: -0.1700

Data Index: 251146 (C4 (Web Text))

Max Activating Token Index: 820

Text #15

Max Range: 7.0852. Min Range: -7.0852

Max Act: 5.9914. Min Act: -0.1700

Data Index: 519859 (C4 (Web Text))

Max Activating Token Index: 213

Text #16

Max Range: 7.0852. Min Range: -7.0852

Max Act: 5.9602. Min Act: -0.1700

Data Index: 253591 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 7.0852. Min Range: -7.0852

Max Act: 5.9602. Min Act: -0.1700

Data Index: 113780 (C4 (Web Text))

Max Activating Token Index: 585

Text #18

Max Range: 7.0852. Min Range: -7.0852

Max Act: 6.0227. Min Act: -0.1700

Data Index: 1245435 (C4 (Web Text))

Max Activating Token Index: 804

Text #19

Max Range: 7.0852. Min Range: -7.0852

Max Act: 5.9914. Min Act: -0.1700

Data Index: 1246441 (C4 (Web Text))

Max Activating Token Index: 133