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

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

Neuron 240 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4139. Min Range: -5.4139

Max Act: 5.4139. Min Act: -0.1700

Data Index: 461399 (C4 (Web Text))

Max Activating Token Index: 1016

Text #1

Max Range: 5.4139. Min Range: -5.4139

Max Act: 5.3514. Min Act: -0.1700

Data Index: 1270319 (C4 (Web Text))

Max Activating Token Index: 539

Text #2

Max Range: 5.4139. Min Range: -5.4139

Max Act: 5.2264. Min Act: -0.1700

Data Index: 450354 (C4 (Web Text))

Max Activating Token Index: 114

Text #3

Max Range: 5.4139. Min Range: -5.4139

Max Act: 5.1951. Min Act: -0.1700

Data Index: 820587 (C4 (Web Text))

Max Activating Token Index: 160

Text #4

Max Range: 5.4139. Min Range: -5.4139

Max Act: 5.1639. Min Act: -0.1700

Data Index: 13023 (C4 (Web Text))

Max Activating Token Index: 442

Text #5

Max Range: 5.4139. Min Range: -5.4139

Max Act: 5.1951. Min Act: -0.1700

Data Index: 1036353 (C4 (Web Text))

Max Activating Token Index: 150

Text #6

Max Range: 5.4139. Min Range: -5.4139

Max Act: 5.1639. Min Act: -0.1700

Data Index: 820754 (C4 (Web Text))

Max Activating Token Index: 76

Text #7

Max Range: 5.4139. Min Range: -5.4139

Max Act: 5.1326. Min Act: -0.1700

Data Index: 1232423 (C4 (Web Text))

Max Activating Token Index: 927

Text #8

Max Range: 5.4139. Min Range: -5.4139

Max Act: 5.1639. Min Act: -0.1700

Data Index: 68612 (C4 (Web Text))

Max Activating Token Index: 697

Text #9

Max Range: 5.4139. Min Range: -5.4139

Max Act: 5.1014. Min Act: -0.1700

Data Index: 158969 (C4 (Web Text))

Max Activating Token Index: 406

Text #10

Max Range: 5.4139. Min Range: -5.4139

Max Act: 5.1326. Min Act: -0.1700

Data Index: 1251358 (C4 (Web Text))

Max Activating Token Index: 704

Text #11

Max Range: 5.4139. Min Range: -5.4139

Max Act: 5.0701. Min Act: -0.1700

Data Index: 716098 (C4 (Web Text))

Max Activating Token Index: 776

Text #12

Max Range: 5.4139. Min Range: -5.4139

Max Act: 5.1326. Min Act: -0.1700

Data Index: 147749 (C4 (Web Text))

Max Activating Token Index: 115

Text #13

Max Range: 5.4139. Min Range: -5.4139

Max Act: 5.1326. Min Act: -0.1700

Data Index: 952455 (C4 (Web Text))

Max Activating Token Index: 685

Text #14

Max Range: 5.4139. Min Range: -5.4139

Max Act: 5.0701. Min Act: -0.1700

Data Index: 585591 (C4 (Web Text))

Max Activating Token Index: 962

Text #15

Max Range: 5.4139. Min Range: -5.4139

Max Act: 5.0701. Min Act: -0.1700

Data Index: 1159384 (C4 (Web Text))

Max Activating Token Index: 430

Text #16

Max Range: 5.4139. Min Range: -5.4139

Max Act: 5.1014. Min Act: -0.1700

Data Index: 935586 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 5.4139. Min Range: -5.4139

Max Act: 5.1639. Min Act: -0.1700

Data Index: 156517 (C4 (Web Text))

Max Activating Token Index: 1016

Text #18

Max Range: 5.4139. Min Range: -5.4139

Max Act: 5.1014. Min Act: -0.1700

Data Index: 84640 (C4 (Web Text))

Max Activating Token Index: 46

Text #19

Max Range: 5.4139. Min Range: -5.4139

Max Act: 5.0701. Min Act: -0.1700

Data Index: 806804 (C4 (Web Text))

Max Activating Token Index: 412