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

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

Neuron 1442 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.6917. Min Range: -5.6917

Max Act: 5.6917. Min Act: -0.1700

Data Index: 652730 (C4 (Web Text))

Max Activating Token Index: 823

Text #1

Max Range: 5.6917. Min Range: -5.6917

Max Act: 5.5042. Min Act: -0.1700

Data Index: 933993 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 5.6917. Min Range: -5.6917

Max Act: 5.2854. Min Act: -0.1700

Data Index: 1281290 (C4 (Web Text))

Max Activating Token Index: 882

Text #3

Max Range: 5.6917. Min Range: -5.6917

Max Act: 5.1292. Min Act: -0.1700

Data Index: 438998 (C4 (Web Text))

Max Activating Token Index: 906

Text #4

Max Range: 5.6917. Min Range: -5.6917

Max Act: 5.2229. Min Act: -0.1700

Data Index: 868887 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 5.6917. Min Range: -5.6917

Max Act: 5.1292. Min Act: -0.1700

Data Index: 879787 (C4 (Web Text))

Max Activating Token Index: 757

Text #6

Max Range: 5.6917. Min Range: -5.6917

Max Act: 5.0979. Min Act: -0.1700

Data Index: 325494 (C4 (Web Text))

Max Activating Token Index: 600

Text #7

Max Range: 5.6917. Min Range: -5.6917

Max Act: 5.0979. Min Act: -0.1700

Data Index: 1280581 (C4 (Web Text))

Max Activating Token Index: 789

Text #8

Max Range: 5.6917. Min Range: -5.6917

Max Act: 5.0354. Min Act: -0.1700

Data Index: 496226 (C4 (Web Text))

Max Activating Token Index: 385

Text #9

Max Range: 5.6917. Min Range: -5.6917

Max Act: 5.0979. Min Act: -0.1700

Data Index: 973893 (C4 (Web Text))

Max Activating Token Index: 834

Text #10

Max Range: 5.6917. Min Range: -5.6917

Max Act: 5.1292. Min Act: -0.1700

Data Index: 474469 (C4 (Web Text))

Max Activating Token Index: 931

Text #11

Max Range: 5.6917. Min Range: -5.6917

Max Act: 5.0354. Min Act: -0.1700

Data Index: 1274929 (C4 (Web Text))

Max Activating Token Index: 611

Text #12

Max Range: 5.6917. Min Range: -5.6917

Max Act: 4.9729. Min Act: -0.1700

Data Index: 334311 (C4 (Web Text))

Max Activating Token Index: 721

Text #13

Max Range: 5.6917. Min Range: -5.6917

Max Act: 5.0667. Min Act: -0.1700

Data Index: 1114788 (C4 (Web Text))

Max Activating Token Index: 295

Text #14

Max Range: 5.6917. Min Range: -5.6917

Max Act: 5.0667. Min Act: -0.1700

Data Index: 502675 (C4 (Web Text))

Max Activating Token Index: 707

Text #15

Max Range: 5.6917. Min Range: -5.6917

Max Act: 4.9417. Min Act: -0.1700

Data Index: 258735 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 5.6917. Min Range: -5.6917

Max Act: 5.0042. Min Act: -0.1700

Data Index: 787180 (C4 (Web Text))

Max Activating Token Index: 685

Text #17

Max Range: 5.6917. Min Range: -5.6917

Max Act: 5.0354. Min Act: -0.1700

Data Index: 1209286 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 5.6917. Min Range: -5.6917

Max Act: 5.0042. Min Act: -0.1700

Data Index: 417926 (C4 (Web Text))

Max Activating Token Index: 284

Text #19

Max Range: 5.6917. Min Range: -5.6917

Max Act: 4.9729. Min Act: -0.1700

Data Index: 851611 (C4 (Web Text))

Max Activating Token Index: 539