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

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

Neuron 1811 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: 5.7639. Min Range: -5.7639

Max Act: 5.7639. Min Act: -0.1700

Data Index: 797366 (C4 (Web Text))

Max Activating Token Index: 198

Text #1

Max Range: 5.7639. Min Range: -5.7639

Max Act: 5.4827. Min Act: -0.1700

Data Index: 25853 (C4 (Web Text))

Max Activating Token Index: 784

Text #2

Max Range: 5.7639. Min Range: -5.7639

Max Act: 5.4827. Min Act: -0.1700

Data Index: 859299 (C4 (Web Text))

Max Activating Token Index: 936

Text #3

Max Range: 5.7639. Min Range: -5.7639

Max Act: 5.4514. Min Act: -0.1700

Data Index: 232085 (C4 (Web Text))

Max Activating Token Index: 581

Text #4

Max Range: 5.7639. Min Range: -5.7639

Max Act: 5.3577. Min Act: -0.1700

Data Index: 595778 (C4 (Web Text))

Max Activating Token Index: 270

Text #5

Max Range: 5.7639. Min Range: -5.7639

Max Act: 5.2639. Min Act: -0.1700

Data Index: 303739 (C4 (Web Text))

Max Activating Token Index: 575

Text #6

Max Range: 5.7639. Min Range: -5.7639

Max Act: 5.3577. Min Act: -0.1700

Data Index: 3738 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 5.7639. Min Range: -5.7639

Max Act: 5.2327. Min Act: -0.1700

Data Index: 1063102 (C4 (Web Text))

Max Activating Token Index: 556

Text #8

Max Range: 5.7639. Min Range: -5.7639

Max Act: 5.2639. Min Act: -0.1700

Data Index: 520941 (C4 (Web Text))

Max Activating Token Index: 385

Text #9

Max Range: 5.7639. Min Range: -5.7639

Max Act: 5.2952. Min Act: -0.1700

Data Index: 1215329 (C4 (Web Text))

Max Activating Token Index: 320

Text #10

Max Range: 5.7639. Min Range: -5.7639

Max Act: 5.2327. Min Act: -0.1700

Data Index: 1105182 (C4 (Web Text))

Max Activating Token Index: 893

Text #11

Max Range: 5.7639. Min Range: -5.7639

Max Act: 5.2639. Min Act: -0.1700

Data Index: 253386 (C4 (Web Text))

Max Activating Token Index: 373

Text #12

Max Range: 5.7639. Min Range: -5.7639

Max Act: 5.2639. Min Act: -0.1700

Data Index: 1087098 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 5.7639. Min Range: -5.7639

Max Act: 5.2639. Min Act: -0.1700

Data Index: 234849 (C4 (Web Text))

Max Activating Token Index: 275

Text #14

Max Range: 5.7639. Min Range: -5.7639

Max Act: 5.2327. Min Act: -0.1700

Data Index: 786848 (C4 (Web Text))

Max Activating Token Index: 360

Text #15

Max Range: 5.7639. Min Range: -5.7639

Max Act: 5.2952. Min Act: -0.1700

Data Index: 793806 (C4 (Web Text))

Max Activating Token Index: 408

Text #16

Max Range: 5.7639. Min Range: -5.7639

Max Act: 5.2639. Min Act: -0.1700

Data Index: 1012383 (C4 (Web Text))

Max Activating Token Index: 303

Text #17

Max Range: 5.7639. Min Range: -5.7639

Max Act: 5.1389. Min Act: -0.1700

Data Index: 365663 (C4 (Web Text))

Max Activating Token Index: 781

Text #18

Max Range: 5.7639. Min Range: -5.7639

Max Act: 5.1702. Min Act: -0.1700

Data Index: 163973 (C4 (Web Text))

Max Activating Token Index: 761

Text #19

Max Range: 5.7639. Min Range: -5.7639

Max Act: 5.1389. Min Act: -0.1700

Data Index: 288762 (C4 (Web Text))

Max Activating Token Index: 114