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

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

Neuron 1354 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: 4.0883. Min Range: -4.0883

Max Act: 4.0883. Min Act: -0.1700

Data Index: 513754 (C4 (Web Text))

Max Activating Token Index: 989

Text #1

Max Range: 4.0883. Min Range: -4.0883

Max Act: 3.9320. Min Act: -0.1700

Data Index: 1543779 (Python Code)

Max Activating Token Index: 978

Text #2

Max Range: 4.0883. Min Range: -4.0883

Max Act: 3.9320. Min Act: -0.1700

Data Index: 1222794 (C4 (Web Text))

Max Activating Token Index: 139

Text #3

Max Range: 4.0883. Min Range: -4.0883

Max Act: 3.8381. Min Act: -0.1700

Data Index: 1370734 (Python Code)

Max Activating Token Index: 1009

Text #4

Max Range: 4.0883. Min Range: -4.0883

Max Act: 3.8069. Min Act: -0.1700

Data Index: 368772 (C4 (Web Text))

Max Activating Token Index: 963

Text #5

Max Range: 4.0883. Min Range: -4.0883

Max Act: 3.8694. Min Act: -0.1700

Data Index: 118659 (C4 (Web Text))

Max Activating Token Index: 836

Text #6

Max Range: 4.0883. Min Range: -4.0883

Max Act: 3.8069. Min Act: -0.1700

Data Index: 89120 (C4 (Web Text))

Max Activating Token Index: 61

Text #7

Max Range: 4.0883. Min Range: -4.0883

Max Act: 3.7756. Min Act: -0.1700

Data Index: 1650271 (Python Code)

Max Activating Token Index: 57

Text #8

Max Range: 4.0883. Min Range: -4.0883

Max Act: 3.7443. Min Act: -0.1700

Data Index: 1395040 (Python Code)

Max Activating Token Index: 398

Text #9

Max Range: 4.0883. Min Range: -4.0883

Max Act: 3.7443. Min Act: -0.1698

Data Index: 704236 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 4.0883. Min Range: -4.0883

Max Act: 3.7443. Min Act: -0.1700

Data Index: 268257 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 4.0883. Min Range: -4.0883

Max Act: 3.7130. Min Act: -0.1700

Data Index: 760834 (C4 (Web Text))

Max Activating Token Index: 65

Text #12

Max Range: 4.0883. Min Range: -4.0883

Max Act: 3.7130. Min Act: -0.1700

Data Index: 272421 (C4 (Web Text))

Max Activating Token Index: 36

Text #13

Max Range: 4.0883. Min Range: -4.0883

Max Act: 3.7130. Min Act: -0.1700

Data Index: 1509686 (Python Code)

Max Activating Token Index: 40

Text #14

Max Range: 4.0883. Min Range: -4.0883

Max Act: 3.7443. Min Act: -0.1700

Data Index: 1571785 (Python Code)

Max Activating Token Index: 905

Text #15

Max Range: 4.0883. Min Range: -4.0883

Max Act: 3.7130. Min Act: -0.1700

Data Index: 1168158 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 4.0883. Min Range: -4.0883

Max Act: 3.6817. Min Act: -0.1700

Data Index: 33590 (C4 (Web Text))

Max Activating Token Index: 773

Text #17

Max Range: 4.0883. Min Range: -4.0883

Max Act: 3.7130. Min Act: -0.1700

Data Index: 40608 (C4 (Web Text))

Max Activating Token Index: 49

Text #18

Max Range: 4.0883. Min Range: -4.0883

Max Act: 3.6817. Min Act: -0.1700

Data Index: 960547 (C4 (Web Text))

Max Activating Token Index: 700

Text #19

Max Range: 4.0883. Min Range: -4.0883

Max Act: 3.6817. Min Act: -0.1700

Data Index: 547629 (C4 (Web Text))

Max Activating Token Index: 920