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

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

Neuron 1959 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: 3.8406. Min Range: -3.8406

Max Act: 3.8406. Min Act: -0.1700

Data Index: 485928 (C4 (Web Text))

Max Activating Token Index: 796

Text #1

Max Range: 3.8406. Min Range: -3.8406

Max Act: 3.8093. Min Act: -0.1700

Data Index: 699409 (C4 (Web Text))

Max Activating Token Index: 912

Text #2

Max Range: 3.8406. Min Range: -3.8406

Max Act: 3.8406. Min Act: -0.1700

Data Index: 310916 (C4 (Web Text))

Max Activating Token Index: 782

Text #3

Max Range: 3.8406. Min Range: -3.8406

Max Act: 3.7780. Min Act: -0.1700

Data Index: 653507 (C4 (Web Text))

Max Activating Token Index: 505

Text #4

Max Range: 3.8406. Min Range: -3.8406

Max Act: 3.7468. Min Act: -0.1700

Data Index: 539484 (C4 (Web Text))

Max Activating Token Index: 147

Text #5

Max Range: 3.8406. Min Range: -3.8406

Max Act: 3.7468. Min Act: -0.1700

Data Index: 551726 (C4 (Web Text))

Max Activating Token Index: 708

Text #6

Max Range: 3.8406. Min Range: -3.8406

Max Act: 3.7468. Min Act: -0.1700

Data Index: 1074316 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 3.8406. Min Range: -3.8406

Max Act: 3.7155. Min Act: -0.1700

Data Index: 539889 (C4 (Web Text))

Max Activating Token Index: 607

Text #8

Max Range: 3.8406. Min Range: -3.8406

Max Act: 3.7468. Min Act: -0.1700

Data Index: 107636 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 3.8406. Min Range: -3.8406

Max Act: 3.7780. Min Act: -0.1700

Data Index: 1169785 (C4 (Web Text))

Max Activating Token Index: 759

Text #10

Max Range: 3.8406. Min Range: -3.8406

Max Act: 3.7468. Min Act: -0.1700

Data Index: 42905 (C4 (Web Text))

Max Activating Token Index: 671

Text #11

Max Range: 3.8406. Min Range: -3.8406

Max Act: 3.7468. Min Act: -0.1700

Data Index: 461465 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 3.8406. Min Range: -3.8406

Max Act: 3.6842. Min Act: -0.1700

Data Index: 854667 (C4 (Web Text))

Max Activating Token Index: 82

Text #13

Max Range: 3.8406. Min Range: -3.8406

Max Act: 3.7155. Min Act: -0.1700

Data Index: 49615 (C4 (Web Text))

Max Activating Token Index: 235

Text #14

Max Range: 3.8406. Min Range: -3.8406

Max Act: 3.6842. Min Act: -0.1699

Data Index: 298523 (C4 (Web Text))

Max Activating Token Index: 613

Text #15

Max Range: 3.8406. Min Range: -3.8406

Max Act: 3.6842. Min Act: -0.1700

Data Index: 131261 (C4 (Web Text))

Max Activating Token Index: 834

Text #16

Max Range: 3.8406. Min Range: -3.8406

Max Act: 3.7155. Min Act: -0.1700

Data Index: 964740 (C4 (Web Text))

Max Activating Token Index: 804

Text #17

Max Range: 3.8406. Min Range: -3.8406

Max Act: 3.6842. Min Act: -0.1700

Data Index: 300751 (C4 (Web Text))

Max Activating Token Index: 304

Text #18

Max Range: 3.8406. Min Range: -3.8406

Max Act: 3.6842. Min Act: -0.1700

Data Index: 736799 (C4 (Web Text))

Max Activating Token Index: 957

Text #19

Max Range: 3.8406. Min Range: -3.8406

Max Act: 3.6842. Min Act: -0.1700

Data Index: 1078244 (C4 (Web Text))

Max Activating Token Index: 843