Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 35 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.7844. Min Range: -4.7844

Max Act: 4.7844. Min Act: -0.1700

Data Index: 1290326 (C4 (Web Text))

Max Activating Token Index: 686

Text #1

Max Range: 4.7844. Min Range: -4.7844

Max Act: 4.7586. Min Act: -0.1700

Data Index: 476703 (C4 (Web Text))

Max Activating Token Index: 756

Text #2

Max Range: 4.7844. Min Range: -4.7844

Max Act: 4.7549. Min Act: -0.1700

Data Index: 272717 (C4 (Web Text))

Max Activating Token Index: 775

Text #3

Max Range: 4.7844. Min Range: -4.7844

Max Act: 4.7510. Min Act: -0.1700

Data Index: 883870 (C4 (Web Text))

Max Activating Token Index: 393

Text #4

Max Range: 4.7844. Min Range: -4.7844

Max Act: 4.6470. Min Act: -0.1700

Data Index: 710017 (C4 (Web Text))

Max Activating Token Index: 941

Text #5

Max Range: 4.7844. Min Range: -4.7844

Max Act: 4.6592. Min Act: -0.1700

Data Index: 1071164 (C4 (Web Text))

Max Activating Token Index: 190

Text #6

Max Range: 4.7844. Min Range: -4.7844

Max Act: 4.6521. Min Act: -0.1700

Data Index: 556657 (C4 (Web Text))

Max Activating Token Index: 324

Text #7

Max Range: 4.7844. Min Range: -4.7844

Max Act: 4.6406. Min Act: -0.1700

Data Index: 1109086 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 4.7844. Min Range: -4.7844

Max Act: 4.6460. Min Act: -0.1700

Data Index: 1134165 (C4 (Web Text))

Max Activating Token Index: 426

Text #9

Max Range: 4.7844. Min Range: -4.7844

Max Act: 4.6604. Min Act: -0.1689

Data Index: 1103869 (C4 (Web Text))

Max Activating Token Index: 337

Text #10

Max Range: 4.7844. Min Range: -4.7844

Max Act: 4.6410. Min Act: -0.1698

Data Index: 487032 (C4 (Web Text))

Max Activating Token Index: 765

Text #11

Max Range: 4.7844. Min Range: -4.7844

Max Act: 4.6377. Min Act: -0.1700

Data Index: 1158818 (C4 (Web Text))

Max Activating Token Index: 68

Text #12

Max Range: 4.7844. Min Range: -4.7844

Max Act: 4.6321. Min Act: -0.1700

Data Index: 438402 (C4 (Web Text))

Max Activating Token Index: 289

Text #13

Max Range: 4.7844. Min Range: -4.7844

Max Act: 4.6483. Min Act: -0.1679

Data Index: 819860 (C4 (Web Text))

Max Activating Token Index: 151

Text #14

Max Range: 4.7844. Min Range: -4.7844

Max Act: 4.6183. Min Act: -0.1700

Data Index: 33034 (C4 (Web Text))

Max Activating Token Index: 911

Text #15

Max Range: 4.7844. Min Range: -4.7844

Max Act: 4.6333. Min Act: -0.1700

Data Index: 476505 (C4 (Web Text))

Max Activating Token Index: 510

Text #16

Max Range: 4.7844. Min Range: -4.7844

Max Act: 4.6023. Min Act: -0.1700

Data Index: 569506 (C4 (Web Text))

Max Activating Token Index: 675

Text #17

Max Range: 4.7844. Min Range: -4.7844

Max Act: 4.5951. Min Act: -0.1700

Data Index: 561985 (C4 (Web Text))

Max Activating Token Index: 399

Text #18

Max Range: 4.7844. Min Range: -4.7844

Max Act: 4.5590. Min Act: -0.1700

Data Index: 594379 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 4.7844. Min Range: -4.7844

Max Act: 4.5769. Min Act: -0.1700

Data Index: 870497 (C4 (Web Text))

Max Activating Token Index: 413