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

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

Neuron 847 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5037. Min Range: -3.5037

Max Act: 3.5037. Min Act: -0.1700

Data Index: 114368 (C4 (Web Text))

Max Activating Token Index: 979

Text #1

Max Range: 3.5037. Min Range: -3.5037

Max Act: 3.4253. Min Act: -0.1700

Data Index: 659760 (C4 (Web Text))

Max Activating Token Index: 896

Text #2

Max Range: 3.5037. Min Range: -3.5037

Max Act: 3.4096. Min Act: -0.1700

Data Index: 865306 (C4 (Web Text))

Max Activating Token Index: 818

Text #3

Max Range: 3.5037. Min Range: -3.5037

Max Act: 3.4253. Min Act: -0.1700

Data Index: 1284564 (C4 (Web Text))

Max Activating Token Index: 670

Text #4

Max Range: 3.5037. Min Range: -3.5037

Max Act: 3.4096. Min Act: -0.1700

Data Index: 1041903 (C4 (Web Text))

Max Activating Token Index: 827

Text #5

Max Range: 3.5037. Min Range: -3.5037

Max Act: 3.4096. Min Act: -0.1700

Data Index: 61039 (C4 (Web Text))

Max Activating Token Index: 733

Text #6

Max Range: 3.5037. Min Range: -3.5037

Max Act: 3.4096. Min Act: -0.1700

Data Index: 948402 (C4 (Web Text))

Max Activating Token Index: 770

Text #7

Max Range: 3.5037. Min Range: -3.5037

Max Act: 3.4253. Min Act: -0.1700

Data Index: 1103587 (C4 (Web Text))

Max Activating Token Index: 688

Text #8

Max Range: 3.5037. Min Range: -3.5037

Max Act: 3.4096. Min Act: -0.1700

Data Index: 312087 (C4 (Web Text))

Max Activating Token Index: 799

Text #9

Max Range: 3.5037. Min Range: -3.5037

Max Act: 3.4096. Min Act: -0.1700

Data Index: 585473 (C4 (Web Text))

Max Activating Token Index: 641

Text #10

Max Range: 3.5037. Min Range: -3.5037

Max Act: 3.3939. Min Act: -0.1700

Data Index: 1090648 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 3.5037. Min Range: -3.5037

Max Act: 3.3783. Min Act: -0.1700

Data Index: 596364 (C4 (Web Text))

Max Activating Token Index: 625

Text #12

Max Range: 3.5037. Min Range: -3.5037

Max Act: 3.3783. Min Act: -0.1700

Data Index: 1129781 (C4 (Web Text))

Max Activating Token Index: 995

Text #13

Max Range: 3.5037. Min Range: -3.5037

Max Act: 3.3783. Min Act: -0.1700

Data Index: 396974 (C4 (Web Text))

Max Activating Token Index: 392

Text #14

Max Range: 3.5037. Min Range: -3.5037

Max Act: 3.3626. Min Act: -0.1700

Data Index: 142064 (C4 (Web Text))

Max Activating Token Index: 673

Text #15

Max Range: 3.5037. Min Range: -3.5037

Max Act: 3.3626. Min Act: -0.1700

Data Index: 549413 (C4 (Web Text))

Max Activating Token Index: 894

Text #16

Max Range: 3.5037. Min Range: -3.5037

Max Act: 3.3626. Min Act: -0.1700

Data Index: 838291 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 3.5037. Min Range: -3.5037

Max Act: 3.3626. Min Act: -0.1700

Data Index: 148891 (C4 (Web Text))

Max Activating Token Index: 952

Text #18

Max Range: 3.5037. Min Range: -3.5037

Max Act: 3.3783. Min Act: -0.1700

Data Index: 1025224 (C4 (Web Text))

Max Activating Token Index: 341

Text #19

Max Range: 3.5037. Min Range: -3.5037

Max Act: 3.3626. Min Act: -0.1700

Data Index: 607753 (C4 (Web Text))

Max Activating Token Index: 671