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

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

Neuron 903 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2055. Min Range: -3.2055

Max Act: 3.2055. Min Act: -0.1700

Data Index: 484586 (C4 (Web Text))

Max Activating Token Index: 930

Text #1

Max Range: 3.2055. Min Range: -3.2055

Max Act: 3.1898. Min Act: -0.1700

Data Index: 342451 (C4 (Web Text))

Max Activating Token Index: 263

Text #2

Max Range: 3.2055. Min Range: -3.2055

Max Act: 3.1583. Min Act: -0.1700

Data Index: 530521 (C4 (Web Text))

Max Activating Token Index: 525

Text #3

Max Range: 3.2055. Min Range: -3.2055

Max Act: 3.0795. Min Act: -0.1700

Data Index: 898886 (C4 (Web Text))

Max Activating Token Index: 230

Text #4

Max Range: 3.2055. Min Range: -3.2055

Max Act: 3.0322. Min Act: -0.1700

Data Index: 815061 (C4 (Web Text))

Max Activating Token Index: 153

Text #5

Max Range: 3.2055. Min Range: -3.2055

Max Act: 3.0322. Min Act: -0.1700

Data Index: 864592 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 3.2055. Min Range: -3.2055

Max Act: 3.0322. Min Act: -0.1700

Data Index: 711358 (C4 (Web Text))

Max Activating Token Index: 96

Text #7

Max Range: 3.2055. Min Range: -3.2055

Max Act: 3.0006. Min Act: -0.1700

Data Index: 1304010 (C4 (Web Text))

Max Activating Token Index: 866

Text #8

Max Range: 3.2055. Min Range: -3.2055

Max Act: 3.0006. Min Act: -0.1700

Data Index: 1249131 (C4 (Web Text))

Max Activating Token Index: 360

Text #9

Max Range: 3.2055. Min Range: -3.2055

Max Act: 3.0006. Min Act: -0.1700

Data Index: 687725 (C4 (Web Text))

Max Activating Token Index: 523

Text #10

Max Range: 3.2055. Min Range: -3.2055

Max Act: 3.0006. Min Act: -0.1700

Data Index: 579785 (C4 (Web Text))

Max Activating Token Index: 422

Text #11

Max Range: 3.2055. Min Range: -3.2055

Max Act: 3.0006. Min Act: -0.1700

Data Index: 500507 (C4 (Web Text))

Max Activating Token Index: 443

Text #12

Max Range: 3.2055. Min Range: -3.2055

Max Act: 2.9689. Min Act: -0.1700

Data Index: 1233628 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 3.2055. Min Range: -3.2055

Max Act: 2.9848. Min Act: -0.1700

Data Index: 851401 (C4 (Web Text))

Max Activating Token Index: 468

Text #14

Max Range: 3.2055. Min Range: -3.2055

Max Act: 2.9848. Min Act: -0.1700

Data Index: 383809 (C4 (Web Text))

Max Activating Token Index: 995

Text #15

Max Range: 3.2055. Min Range: -3.2055

Max Act: 2.9531. Min Act: -0.1700

Data Index: 42237 (C4 (Web Text))

Max Activating Token Index: 667

Text #16

Max Range: 3.2055. Min Range: -3.2055

Max Act: 2.9848. Min Act: -0.1700

Data Index: 1301359 (C4 (Web Text))

Max Activating Token Index: 383

Text #17

Max Range: 3.2055. Min Range: -3.2055

Max Act: 2.9689. Min Act: -0.1700

Data Index: 259677 (C4 (Web Text))

Max Activating Token Index: 1013

Text #18

Max Range: 3.2055. Min Range: -3.2055

Max Act: 2.9531. Min Act: -0.1700

Data Index: 1048958 (C4 (Web Text))

Max Activating Token Index: 430

Text #19

Max Range: 3.2055. Min Range: -3.2055

Max Act: 2.9531. Min Act: -0.1700

Data Index: 871373 (C4 (Web Text))

Max Activating Token Index: 636