Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 778 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.0886. Min Range: -5.0886

Max Act: 5.0886. Min Act: -0.1700

Data Index: 1183288 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 5.0886. Min Range: -5.0886

Max Act: 5.0886. Min Act: -0.1700

Data Index: 640580 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 5.0886. Min Range: -5.0886

Max Act: 5.0573. Min Act: -0.1700

Data Index: 1320722 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 5.0886. Min Range: -5.0886

Max Act: 5.0261. Min Act: -0.1700

Data Index: 492680 (C4 (Web Text))

Max Activating Token Index: 961

Text #4

Max Range: 5.0886. Min Range: -5.0886

Max Act: 4.9948. Min Act: -0.1700

Data Index: 693134 (C4 (Web Text))

Max Activating Token Index: 1005

Text #5

Max Range: 5.0886. Min Range: -5.0886

Max Act: 5.0261. Min Act: -0.1700

Data Index: 104623 (C4 (Web Text))

Max Activating Token Index: 1004

Text #6

Max Range: 5.0886. Min Range: -5.0886

Max Act: 5.0261. Min Act: -0.1700

Data Index: 650857 (C4 (Web Text))

Max Activating Token Index: 827

Text #7

Max Range: 5.0886. Min Range: -5.0886

Max Act: 4.9948. Min Act: -0.1700

Data Index: 1057646 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 5.0886. Min Range: -5.0886

Max Act: 5.0261. Min Act: -0.1700

Data Index: 538455 (C4 (Web Text))

Max Activating Token Index: 407

Text #9

Max Range: 5.0886. Min Range: -5.0886

Max Act: 5.0261. Min Act: -0.1700

Data Index: 308546 (C4 (Web Text))

Max Activating Token Index: 309

Text #10

Max Range: 5.0886. Min Range: -5.0886

Max Act: 4.9636. Min Act: -0.1700

Data Index: 1264020 (C4 (Web Text))

Max Activating Token Index: 407

Text #11

Max Range: 5.0886. Min Range: -5.0886

Max Act: 4.9948. Min Act: -0.1700

Data Index: 1252343 (C4 (Web Text))

Max Activating Token Index: 879

Text #12

Max Range: 5.0886. Min Range: -5.0886

Max Act: 4.9011. Min Act: -0.1700

Data Index: 47012 (C4 (Web Text))

Max Activating Token Index: 791

Text #13

Max Range: 5.0886. Min Range: -5.0886

Max Act: 4.9323. Min Act: -0.1700

Data Index: 619758 (C4 (Web Text))

Max Activating Token Index: 576

Text #14

Max Range: 5.0886. Min Range: -5.0886

Max Act: 4.9323. Min Act: -0.1700

Data Index: 654972 (C4 (Web Text))

Max Activating Token Index: 315

Text #15

Max Range: 5.0886. Min Range: -5.0886

Max Act: 4.9636. Min Act: -0.1700

Data Index: 366764 (C4 (Web Text))

Max Activating Token Index: 994

Text #16

Max Range: 5.0886. Min Range: -5.0886

Max Act: 4.9011. Min Act: -0.1700

Data Index: 924738 (C4 (Web Text))

Max Activating Token Index: 891

Text #17

Max Range: 5.0886. Min Range: -5.0886

Max Act: 4.9323. Min Act: -0.1700

Data Index: 1085889 (C4 (Web Text))

Max Activating Token Index: 990

Text #18

Max Range: 5.0886. Min Range: -5.0886

Max Act: 4.9011. Min Act: -0.1700

Data Index: 518583 (C4 (Web Text))

Max Activating Token Index: 454

Text #19

Max Range: 5.0886. Min Range: -5.0886

Max Act: 4.9636. Min Act: -0.1700

Data Index: 567149 (C4 (Web Text))

Max Activating Token Index: 933