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

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

Neuron 1582 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6664. Min Range: -3.6664

Max Act: 3.6351. Min Act: -0.1700

Data Index: 121928 (C4 (Web Text))

Max Activating Token Index: 443

Text #1

Max Range: 3.6664. Min Range: -3.6664

Max Act: 3.5725. Min Act: -0.1700

Data Index: 994103 (C4 (Web Text))

Max Activating Token Index: 491

Text #2

Max Range: 3.6664. Min Range: -3.6664

Max Act: 3.6664. Min Act: -0.1700

Data Index: 970758 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 3.6664. Min Range: -3.6664

Max Act: 3.6664. Min Act: -0.1700

Data Index: 60320 (C4 (Web Text))

Max Activating Token Index: 1003

Text #4

Max Range: 3.6664. Min Range: -3.6664

Max Act: 3.6351. Min Act: -0.1700

Data Index: 443939 (C4 (Web Text))

Max Activating Token Index: 151

Text #5

Max Range: 3.6664. Min Range: -3.6664

Max Act: 3.6038. Min Act: -0.1700

Data Index: 988094 (C4 (Web Text))

Max Activating Token Index: 376

Text #6

Max Range: 3.6664. Min Range: -3.6664

Max Act: 3.5725. Min Act: -0.1700

Data Index: 617226 (C4 (Web Text))

Max Activating Token Index: 712

Text #7

Max Range: 3.6664. Min Range: -3.6664

Max Act: 3.5098. Min Act: -0.1700

Data Index: 1036549 (C4 (Web Text))

Max Activating Token Index: 999

Text #8

Max Range: 3.6664. Min Range: -3.6664

Max Act: 3.5725. Min Act: -0.1700

Data Index: 1140231 (C4 (Web Text))

Max Activating Token Index: 830

Text #9

Max Range: 3.6664. Min Range: -3.6664

Max Act: 3.5725. Min Act: -0.1700

Data Index: 524526 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 3.6664. Min Range: -3.6664

Max Act: 3.5725. Min Act: -0.1700

Data Index: 661627 (C4 (Web Text))

Max Activating Token Index: 436

Text #11

Max Range: 3.6664. Min Range: -3.6664

Max Act: 3.5725. Min Act: -0.1700

Data Index: 642876 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 3.6664. Min Range: -3.6664

Max Act: 3.5725. Min Act: -0.1700

Data Index: 100615 (C4 (Web Text))

Max Activating Token Index: 869

Text #13

Max Range: 3.6664. Min Range: -3.6664

Max Act: 3.4785. Min Act: -0.1700

Data Index: 996437 (C4 (Web Text))

Max Activating Token Index: 513

Text #14

Max Range: 3.6664. Min Range: -3.6664

Max Act: 3.5412. Min Act: -0.1700

Data Index: 729896 (C4 (Web Text))

Max Activating Token Index: 186

Text #15

Max Range: 3.6664. Min Range: -3.6664

Max Act: 3.5412. Min Act: -0.1700

Data Index: 823834 (C4 (Web Text))

Max Activating Token Index: 473

Text #16

Max Range: 3.6664. Min Range: -3.6664

Max Act: 3.5412. Min Act: -0.1700

Data Index: 813157 (C4 (Web Text))

Max Activating Token Index: 96

Text #17

Max Range: 3.6664. Min Range: -3.6664

Max Act: 3.5412. Min Act: -0.1700

Data Index: 809437 (C4 (Web Text))

Max Activating Token Index: 910

Text #18

Max Range: 3.6664. Min Range: -3.6664

Max Act: 3.4785. Min Act: -0.1700

Data Index: 166583 (C4 (Web Text))

Max Activating Token Index: 461

Text #19

Max Range: 3.6664. Min Range: -3.6664

Max Act: 3.5098. Min Act: -0.1700

Data Index: 639285 (C4 (Web Text))

Max Activating Token Index: 812