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

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

Neuron 1421 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: 3.8296. Min Range: -3.8296

Max Act: 3.7983. Min Act: -0.1700

Data Index: 692374 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 3.8296. Min Range: -3.8296

Max Act: 3.8296. Min Act: -0.1700

Data Index: 659837 (C4 (Web Text))

Max Activating Token Index: 501

Text #2

Max Range: 3.8296. Min Range: -3.8296

Max Act: 3.7983. Min Act: -0.1700

Data Index: 406725 (C4 (Web Text))

Max Activating Token Index: 63

Text #3

Max Range: 3.8296. Min Range: -3.8296

Max Act: 3.7983. Min Act: -0.1700

Data Index: 1021406 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 3.8296. Min Range: -3.8296

Max Act: 3.7983. Min Act: -0.1700

Data Index: 666043 (C4 (Web Text))

Max Activating Token Index: 222

Text #5

Max Range: 3.8296. Min Range: -3.8296

Max Act: 3.7670. Min Act: -0.1700

Data Index: 518469 (C4 (Web Text))

Max Activating Token Index: 446

Text #6

Max Range: 3.8296. Min Range: -3.8296

Max Act: 3.7983. Min Act: -0.1700

Data Index: 582547 (C4 (Web Text))

Max Activating Token Index: 479

Text #7

Max Range: 3.8296. Min Range: -3.8296

Max Act: 3.7670. Min Act: -0.1700

Data Index: 981304 (C4 (Web Text))

Max Activating Token Index: 762

Text #8

Max Range: 3.8296. Min Range: -3.8296

Max Act: 3.7670. Min Act: -0.1700

Data Index: 129737 (C4 (Web Text))

Max Activating Token Index: 703

Text #9

Max Range: 3.8296. Min Range: -3.8296

Max Act: 3.7983. Min Act: -0.1700

Data Index: 443052 (C4 (Web Text))

Max Activating Token Index: 553

Text #10

Max Range: 3.8296. Min Range: -3.8296

Max Act: 3.7670. Min Act: -0.1700

Data Index: 706149 (C4 (Web Text))

Max Activating Token Index: 823

Text #11

Max Range: 3.8296. Min Range: -3.8296

Max Act: 3.7670. Min Act: -0.1700

Data Index: 388722 (C4 (Web Text))

Max Activating Token Index: 507

Text #12

Max Range: 3.8296. Min Range: -3.8296

Max Act: 3.7670. Min Act: -0.1700

Data Index: 870160 (C4 (Web Text))

Max Activating Token Index: 816

Text #13

Max Range: 3.8296. Min Range: -3.8296

Max Act: 3.7670. Min Act: -0.1700

Data Index: 901521 (C4 (Web Text))

Max Activating Token Index: 390

Text #14

Max Range: 3.8296. Min Range: -3.8296

Max Act: 3.7670. Min Act: -0.1700

Data Index: 588566 (C4 (Web Text))

Max Activating Token Index: 372

Text #15

Max Range: 3.8296. Min Range: -3.8296

Max Act: 3.7670. Min Act: -0.1700

Data Index: 671929 (C4 (Web Text))

Max Activating Token Index: 568

Text #16

Max Range: 3.8296. Min Range: -3.8296

Max Act: 3.7670. Min Act: -0.1700

Data Index: 20691 (C4 (Web Text))

Max Activating Token Index: 167

Text #17

Max Range: 3.8296. Min Range: -3.8296

Max Act: 3.7358. Min Act: -0.1700

Data Index: 1014589 (C4 (Web Text))

Max Activating Token Index: 454

Text #18

Max Range: 3.8296. Min Range: -3.8296

Max Act: 3.7670. Min Act: -0.1700

Data Index: 1151352 (C4 (Web Text))

Max Activating Token Index: 635

Text #19

Max Range: 3.8296. Min Range: -3.8296

Max Act: 3.7670. Min Act: -0.1700

Data Index: 929211 (C4 (Web Text))

Max Activating Token Index: 15