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

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

Neuron 257 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7813. Min Range: -3.7813

Max Act: 3.7188. Min Act: -0.1700

Data Index: 600033 (C4 (Web Text))

Max Activating Token Index: 545

Text #1

Max Range: 3.7813. Min Range: -3.7813

Max Act: 3.7188. Min Act: -0.1700

Data Index: 283170 (C4 (Web Text))

Max Activating Token Index: 648

Text #2

Max Range: 3.7813. Min Range: -3.7813

Max Act: 3.7188. Min Act: -0.1700

Data Index: 1090539 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 3.7813. Min Range: -3.7813

Max Act: 3.7813. Min Act: -0.1700

Data Index: 780448 (C4 (Web Text))

Max Activating Token Index: 732

Text #4

Max Range: 3.7813. Min Range: -3.7813

Max Act: 3.7188. Min Act: -0.1699

Data Index: 746415 (C4 (Web Text))

Max Activating Token Index: 563

Text #5

Max Range: 3.7813. Min Range: -3.7813

Max Act: 3.6249. Min Act: -0.1700

Data Index: 1196870 (C4 (Web Text))

Max Activating Token Index: 267

Text #6

Max Range: 3.7813. Min Range: -3.7813

Max Act: 3.6875. Min Act: -0.1700

Data Index: 106226 (C4 (Web Text))

Max Activating Token Index: 172

Text #7

Max Range: 3.7813. Min Range: -3.7813

Max Act: 3.6249. Min Act: -0.1700

Data Index: 660007 (C4 (Web Text))

Max Activating Token Index: 623

Text #8

Max Range: 3.7813. Min Range: -3.7813

Max Act: 3.6249. Min Act: -0.1700

Data Index: 1179784 (C4 (Web Text))

Max Activating Token Index: 571

Text #9

Max Range: 3.7813. Min Range: -3.7813

Max Act: 3.6249. Min Act: -0.1700

Data Index: 496243 (C4 (Web Text))

Max Activating Token Index: 759

Text #10

Max Range: 3.7813. Min Range: -3.7813

Max Act: 3.5936. Min Act: -0.1700

Data Index: 391486 (C4 (Web Text))

Max Activating Token Index: 758

Text #11

Max Range: 3.7813. Min Range: -3.7813

Max Act: 3.6562. Min Act: -0.1700

Data Index: 229193 (C4 (Web Text))

Max Activating Token Index: 544

Text #12

Max Range: 3.7813. Min Range: -3.7813

Max Act: 3.6562. Min Act: -0.1700

Data Index: 243688 (C4 (Web Text))

Max Activating Token Index: 571

Text #13

Max Range: 3.7813. Min Range: -3.7813

Max Act: 3.6249. Min Act: -0.1700

Data Index: 811352 (C4 (Web Text))

Max Activating Token Index: 458

Text #14

Max Range: 3.7813. Min Range: -3.7813

Max Act: 3.6875. Min Act: -0.1700

Data Index: 1059342 (C4 (Web Text))

Max Activating Token Index: 421

Text #15

Max Range: 3.7813. Min Range: -3.7813

Max Act: 3.5779. Min Act: -0.1700

Data Index: 1034869 (C4 (Web Text))

Max Activating Token Index: 905

Text #16

Max Range: 3.7813. Min Range: -3.7813

Max Act: 3.5779. Min Act: -0.1700

Data Index: 930520 (C4 (Web Text))

Max Activating Token Index: 536

Text #17

Max Range: 3.7813. Min Range: -3.7813

Max Act: 3.5622. Min Act: -0.1699

Data Index: 1285802 (C4 (Web Text))

Max Activating Token Index: 925

Text #18

Max Range: 3.7813. Min Range: -3.7813

Max Act: 3.5622. Min Act: -0.1700

Data Index: 553459 (C4 (Web Text))

Max Activating Token Index: 802

Text #19

Max Range: 3.7813. Min Range: -3.7813

Max Act: 3.5309. Min Act: -0.1700

Data Index: 591346 (C4 (Web Text))

Max Activating Token Index: 765