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

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

Neuron 1317 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8798. Min Range: -5.8798

Max Act: 5.8798. Min Act: -0.1700

Data Index: 622292 (C4 (Web Text))

Max Activating Token Index: 455

Text #1

Max Range: 5.8798. Min Range: -5.8798

Max Act: 5.8173. Min Act: -0.1700

Data Index: 389528 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 5.8798. Min Range: -5.8798

Max Act: 5.6298. Min Act: -0.1700

Data Index: 169003 (C4 (Web Text))

Max Activating Token Index: 524

Text #3

Max Range: 5.8798. Min Range: -5.8798

Max Act: 5.5673. Min Act: -0.1700

Data Index: 25641 (C4 (Web Text))

Max Activating Token Index: 312

Text #4

Max Range: 5.8798. Min Range: -5.8798

Max Act: 5.5673. Min Act: -0.1700

Data Index: 942190 (C4 (Web Text))

Max Activating Token Index: 261

Text #5

Max Range: 5.8798. Min Range: -5.8798

Max Act: 5.5360. Min Act: -0.1700

Data Index: 1343385 (C4 (Web Text))

Max Activating Token Index: 736

Text #6

Max Range: 5.8798. Min Range: -5.8798

Max Act: 5.5673. Min Act: -0.1700

Data Index: 516275 (C4 (Web Text))

Max Activating Token Index: 820

Text #7

Max Range: 5.8798. Min Range: -5.8798

Max Act: 5.5048. Min Act: -0.1671

Data Index: 749088 (C4 (Web Text))

Max Activating Token Index: 422

Text #8

Max Range: 5.8798. Min Range: -5.8798

Max Act: 5.5360. Min Act: -0.1699

Data Index: 403251 (C4 (Web Text))

Max Activating Token Index: 331

Text #9

Max Range: 5.8798. Min Range: -5.8798

Max Act: 5.4735. Min Act: -0.1700

Data Index: 99329 (C4 (Web Text))

Max Activating Token Index: 444

Text #10

Max Range: 5.8798. Min Range: -5.8798

Max Act: 5.4735. Min Act: -0.1697

Data Index: 409514 (C4 (Web Text))

Max Activating Token Index: 262

Text #11

Max Range: 5.8798. Min Range: -5.8798

Max Act: 5.4735. Min Act: -0.1700

Data Index: 1348066 (C4 (Web Text))

Max Activating Token Index: 430

Text #12

Max Range: 5.8798. Min Range: -5.8798

Max Act: 5.4423. Min Act: -0.1700

Data Index: 1040246 (C4 (Web Text))

Max Activating Token Index: 622

Text #13

Max Range: 5.8798. Min Range: -5.8798

Max Act: 5.4423. Min Act: -0.1700

Data Index: 646820 (C4 (Web Text))

Max Activating Token Index: 492

Text #14

Max Range: 5.8798. Min Range: -5.8798

Max Act: 5.4423. Min Act: -0.1700

Data Index: 1050085 (C4 (Web Text))

Max Activating Token Index: 357

Text #15

Max Range: 5.8798. Min Range: -5.8798

Max Act: 5.4110. Min Act: -0.1700

Data Index: 1197500 (C4 (Web Text))

Max Activating Token Index: 1007

Text #16

Max Range: 5.8798. Min Range: -5.8798

Max Act: 5.4423. Min Act: -0.1700

Data Index: 752370 (C4 (Web Text))

Max Activating Token Index: 337

Text #17

Max Range: 5.8798. Min Range: -5.8798

Max Act: 5.4110. Min Act: -0.1699

Data Index: 252675 (C4 (Web Text))

Max Activating Token Index: 845

Text #18

Max Range: 5.8798. Min Range: -5.8798

Max Act: 5.4423. Min Act: -0.1700

Data Index: 129871 (C4 (Web Text))

Max Activating Token Index: 630

Text #19

Max Range: 5.8798. Min Range: -5.8798

Max Act: 5.4110. Min Act: -0.1700

Data Index: 117501 (C4 (Web Text))

Max Activating Token Index: 1006