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

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

Neuron 1889 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: 5.1863. Min Range: -5.1863

Max Act: 5.1863. Min Act: -0.1700

Data Index: 773176 (C4 (Web Text))

Max Activating Token Index: 941

Text #1

Max Range: 5.1863. Min Range: -5.1863

Max Act: 5.1863. Min Act: -0.1700

Data Index: 110762 (C4 (Web Text))

Max Activating Token Index: 941

Text #2

Max Range: 5.1863. Min Range: -5.1863

Max Act: 5.0613. Min Act: -0.1700

Data Index: 1319059 (C4 (Web Text))

Max Activating Token Index: 461

Text #3

Max Range: 5.1863. Min Range: -5.1863

Max Act: 5.0301. Min Act: -0.1700

Data Index: 200257 (C4 (Web Text))

Max Activating Token Index: 181

Text #4

Max Range: 5.1863. Min Range: -5.1863

Max Act: 5.0301. Min Act: -0.1700

Data Index: 420883 (C4 (Web Text))

Max Activating Token Index: 1005

Text #5

Max Range: 5.1863. Min Range: -5.1863

Max Act: 4.9363. Min Act: -0.1700

Data Index: 627732 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 5.1863. Min Range: -5.1863

Max Act: 4.9363. Min Act: -0.1700

Data Index: 296497 (C4 (Web Text))

Max Activating Token Index: 751

Text #7

Max Range: 5.1863. Min Range: -5.1863

Max Act: 4.9363. Min Act: -0.1700

Data Index: 1063454 (C4 (Web Text))

Max Activating Token Index: 834

Text #8

Max Range: 5.1863. Min Range: -5.1863

Max Act: 4.8738. Min Act: -0.1700

Data Index: 147313 (C4 (Web Text))

Max Activating Token Index: 931

Text #9

Max Range: 5.1863. Min Range: -5.1863

Max Act: 4.9363. Min Act: -0.1700

Data Index: 1318947 (C4 (Web Text))

Max Activating Token Index: 821

Text #10

Max Range: 5.1863. Min Range: -5.1863

Max Act: 4.9363. Min Act: -0.1700

Data Index: 730173 (C4 (Web Text))

Max Activating Token Index: 594

Text #11

Max Range: 5.1863. Min Range: -5.1863

Max Act: 4.9050. Min Act: -0.1700

Data Index: 538141 (C4 (Web Text))

Max Activating Token Index: 829

Text #12

Max Range: 5.1863. Min Range: -5.1863

Max Act: 4.8425. Min Act: -0.1700

Data Index: 11037 (C4 (Web Text))

Max Activating Token Index: 930

Text #13

Max Range: 5.1863. Min Range: -5.1863

Max Act: 4.8738. Min Act: -0.1700

Data Index: 445038 (C4 (Web Text))

Max Activating Token Index: 665

Text #14

Max Range: 5.1863. Min Range: -5.1863

Max Act: 4.8425. Min Act: -0.1700

Data Index: 620672 (C4 (Web Text))

Max Activating Token Index: 701

Text #15

Max Range: 5.1863. Min Range: -5.1863

Max Act: 4.7488. Min Act: -0.1700

Data Index: 170028 (C4 (Web Text))

Max Activating Token Index: 289

Text #16

Max Range: 5.1863. Min Range: -5.1863

Max Act: 4.7800. Min Act: -0.1700

Data Index: 167766 (C4 (Web Text))

Max Activating Token Index: 157

Text #17

Max Range: 5.1863. Min Range: -5.1863

Max Act: 4.7488. Min Act: -0.1700

Data Index: 817161 (C4 (Web Text))

Max Activating Token Index: 119

Text #18

Max Range: 5.1863. Min Range: -5.1863

Max Act: 4.7488. Min Act: -0.1700

Data Index: 925026 (C4 (Web Text))

Max Activating Token Index: 982

Text #19

Max Range: 5.1863. Min Range: -5.1863

Max Act: 4.7488. Min Act: -0.1700

Data Index: 929139 (C4 (Web Text))

Max Activating Token Index: 532