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

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

Neuron 1443 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: 3.7075. Min Range: -3.7075

Max Act: 3.7075. Min Act: -0.1700

Data Index: 1513030 (Python Code)

Max Activating Token Index: 381

Text #1

Max Range: 3.7075. Min Range: -3.7075

Max Act: 3.4569. Min Act: -0.1700

Data Index: 1400279 (Python Code)

Max Activating Token Index: 644

Text #2

Max Range: 3.7075. Min Range: -3.7075

Max Act: 3.4256. Min Act: -0.1700

Data Index: 392067 (C4 (Web Text))

Max Activating Token Index: 432

Text #3

Max Range: 3.7075. Min Range: -3.7075

Max Act: 3.4256. Min Act: -0.1700

Data Index: 524858 (C4 (Web Text))

Max Activating Token Index: 804

Text #4

Max Range: 3.7075. Min Range: -3.7075

Max Act: 3.4256. Min Act: -0.1700

Data Index: 1224104 (C4 (Web Text))

Max Activating Token Index: 744

Text #5

Max Range: 3.7075. Min Range: -3.7075

Max Act: 3.3785. Min Act: -0.1700

Data Index: 1303165 (C4 (Web Text))

Max Activating Token Index: 675

Text #6

Max Range: 3.7075. Min Range: -3.7075

Max Act: 3.3942. Min Act: -0.1700

Data Index: 1621923 (Python Code)

Max Activating Token Index: 470

Text #7

Max Range: 3.7075. Min Range: -3.7075

Max Act: 3.3942. Min Act: -0.1700

Data Index: 1275832 (C4 (Web Text))

Max Activating Token Index: 642

Text #8

Max Range: 3.7075. Min Range: -3.7075

Max Act: 3.3785. Min Act: -0.1700

Data Index: 746806 (C4 (Web Text))

Max Activating Token Index: 141

Text #9

Max Range: 3.7075. Min Range: -3.7075

Max Act: 3.3785. Min Act: -0.1700

Data Index: 92498 (C4 (Web Text))

Max Activating Token Index: 679

Text #10

Max Range: 3.7075. Min Range: -3.7075

Max Act: 3.3471. Min Act: -0.1700

Data Index: 782589 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 3.7075. Min Range: -3.7075

Max Act: 3.3471. Min Act: -0.1700

Data Index: 1318208 (C4 (Web Text))

Max Activating Token Index: 372

Text #12

Max Range: 3.7075. Min Range: -3.7075

Max Act: 3.3628. Min Act: -0.1700

Data Index: 946085 (C4 (Web Text))

Max Activating Token Index: 622

Text #13

Max Range: 3.7075. Min Range: -3.7075

Max Act: 3.3628. Min Act: -0.1700

Data Index: 163121 (C4 (Web Text))

Max Activating Token Index: 695

Text #14

Max Range: 3.7075. Min Range: -3.7075

Max Act: 3.3471. Min Act: -0.1700

Data Index: 453463 (C4 (Web Text))

Max Activating Token Index: 647

Text #15

Max Range: 3.7075. Min Range: -3.7075

Max Act: 3.3157. Min Act: -0.1700

Data Index: 621981 (C4 (Web Text))

Max Activating Token Index: 593

Text #16

Max Range: 3.7075. Min Range: -3.7075

Max Act: 3.3314. Min Act: -0.1700

Data Index: 852478 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 3.7075. Min Range: -3.7075

Max Act: 3.3314. Min Act: -0.1700

Data Index: 600351 (C4 (Web Text))

Max Activating Token Index: 371

Text #18

Max Range: 3.7075. Min Range: -3.7075

Max Act: 3.3314. Min Act: -0.1700

Data Index: 160150 (C4 (Web Text))

Max Activating Token Index: 787

Text #19

Max Range: 3.7075. Min Range: -3.7075

Max Act: 3.3314. Min Act: -0.1700

Data Index: 420333 (C4 (Web Text))

Max Activating Token Index: 869