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

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

Neuron 864 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: 5.9544. Min Range: -5.9544

Max Act: 5.9544. Min Act: -0.1700

Data Index: 1254401 (C4 (Web Text))

Max Activating Token Index: 278

Text #1

Max Range: 5.9544. Min Range: -5.9544

Max Act: 5.8919. Min Act: -0.1700

Data Index: 295690 (C4 (Web Text))

Max Activating Token Index: 201

Text #2

Max Range: 5.9544. Min Range: -5.9544

Max Act: 5.8606. Min Act: -0.1700

Data Index: 412229 (C4 (Web Text))

Max Activating Token Index: 855

Text #3

Max Range: 5.9544. Min Range: -5.9544

Max Act: 5.7669. Min Act: -0.1700

Data Index: 1020794 (C4 (Web Text))

Max Activating Token Index: 252

Text #4

Max Range: 5.9544. Min Range: -5.9544

Max Act: 5.7669. Min Act: -0.1700

Data Index: 463379 (C4 (Web Text))

Max Activating Token Index: 899

Text #5

Max Range: 5.9544. Min Range: -5.9544

Max Act: 5.7356. Min Act: -0.1700

Data Index: 984146 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 5.9544. Min Range: -5.9544

Max Act: 5.7669. Min Act: -0.1700

Data Index: 899439 (C4 (Web Text))

Max Activating Token Index: 792

Text #7

Max Range: 5.9544. Min Range: -5.9544

Max Act: 5.8294. Min Act: -0.1700

Data Index: 521751 (C4 (Web Text))

Max Activating Token Index: 709

Text #8

Max Range: 5.9544. Min Range: -5.9544

Max Act: 5.7669. Min Act: -0.1700

Data Index: 1034352 (C4 (Web Text))

Max Activating Token Index: 228

Text #9

Max Range: 5.9544. Min Range: -5.9544

Max Act: 5.7356. Min Act: -0.1700

Data Index: 522608 (C4 (Web Text))

Max Activating Token Index: 831

Text #10

Max Range: 5.9544. Min Range: -5.9544

Max Act: 5.7981. Min Act: -0.1700

Data Index: 493406 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 5.9544. Min Range: -5.9544

Max Act: 5.7356. Min Act: -0.1700

Data Index: 909443 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 5.9544. Min Range: -5.9544

Max Act: 5.7044. Min Act: -0.1700

Data Index: 1168501 (C4 (Web Text))

Max Activating Token Index: 181

Text #13

Max Range: 5.9544. Min Range: -5.9544

Max Act: 5.7044. Min Act: -0.1700

Data Index: 1148114 (C4 (Web Text))

Max Activating Token Index: 406

Text #14

Max Range: 5.9544. Min Range: -5.9544

Max Act: 5.7356. Min Act: -0.1700

Data Index: 350103 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 5.9544. Min Range: -5.9544

Max Act: 5.6106. Min Act: -0.1700

Data Index: 219732 (C4 (Web Text))

Max Activating Token Index: 744

Text #16

Max Range: 5.9544. Min Range: -5.9544

Max Act: 5.6419. Min Act: -0.1700

Data Index: 51272 (C4 (Web Text))

Max Activating Token Index: 747

Text #17

Max Range: 5.9544. Min Range: -5.9544

Max Act: 5.6731. Min Act: -0.1700

Data Index: 336260 (C4 (Web Text))

Max Activating Token Index: 946

Text #18

Max Range: 5.9544. Min Range: -5.9544

Max Act: 5.5481. Min Act: -0.1700

Data Index: 161550 (C4 (Web Text))

Max Activating Token Index: 910

Text #19

Max Range: 5.9544. Min Range: -5.9544

Max Act: 5.6106. Min Act: -0.1700

Data Index: 315167 (C4 (Web Text))

Max Activating Token Index: 412