Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1084 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 8.9704. Min Range: -8.9704

Max Act: 8.9704. Min Act: -0.1700

Data Index: 1427894 (Python Code)

Max Activating Token Index: 275

Text #1

Max Range: 8.9704. Min Range: -8.9704

Max Act: 8.6579. Min Act: -0.1700

Data Index: 851236 (C4 (Web Text))

Max Activating Token Index: 182

Text #2

Max Range: 8.9704. Min Range: -8.9704

Max Act: 8.4704. Min Act: -0.1700

Data Index: 465235 (C4 (Web Text))

Max Activating Token Index: 344

Text #3

Max Range: 8.9704. Min Range: -8.9704

Max Act: 8.3454. Min Act: -0.1700

Data Index: 244070 (C4 (Web Text))

Max Activating Token Index: 358

Text #4

Max Range: 8.9704. Min Range: -8.9704

Max Act: 8.4079. Min Act: -0.1700

Data Index: 536483 (C4 (Web Text))

Max Activating Token Index: 789

Text #5

Max Range: 8.9704. Min Range: -8.9704

Max Act: 8.5329. Min Act: -0.1700

Data Index: 716225 (C4 (Web Text))

Max Activating Token Index: 692

Text #6

Max Range: 8.9704. Min Range: -8.9704

Max Act: 8.4704. Min Act: -0.1700

Data Index: 387616 (C4 (Web Text))

Max Activating Token Index: 982

Text #7

Max Range: 8.9704. Min Range: -8.9704

Max Act: 8.3454. Min Act: -0.1700

Data Index: 403153 (C4 (Web Text))

Max Activating Token Index: 763

Text #8

Max Range: 8.9704. Min Range: -8.9704

Max Act: 8.1892. Min Act: -0.1700

Data Index: 108579 (C4 (Web Text))

Max Activating Token Index: 273

Text #9

Max Range: 8.9704. Min Range: -8.9704

Max Act: 8.2829. Min Act: -0.1699

Data Index: 4489 (C4 (Web Text))

Max Activating Token Index: 404

Text #10

Max Range: 8.9704. Min Range: -8.9704

Max Act: 8.1579. Min Act: -0.1700

Data Index: 325574 (C4 (Web Text))

Max Activating Token Index: 703

Text #11

Max Range: 8.9704. Min Range: -8.9704

Max Act: 8.2204. Min Act: -0.1700

Data Index: 1310871 (C4 (Web Text))

Max Activating Token Index: 737

Text #12

Max Range: 8.9704. Min Range: -8.9704

Max Act: 8.1892. Min Act: -0.1700

Data Index: 158581 (C4 (Web Text))

Max Activating Token Index: 132

Text #13

Max Range: 8.9704. Min Range: -8.9704

Max Act: 8.1579. Min Act: -0.1700

Data Index: 528494 (C4 (Web Text))

Max Activating Token Index: 957

Text #14

Max Range: 8.9704. Min Range: -8.9704

Max Act: 8.0329. Min Act: -0.1700

Data Index: 1141499 (C4 (Web Text))

Max Activating Token Index: 232

Text #15

Max Range: 8.9704. Min Range: -8.9704

Max Act: 8.0642. Min Act: -0.1699

Data Index: 1100027 (C4 (Web Text))

Max Activating Token Index: 575

Text #16

Max Range: 8.9704. Min Range: -8.9704

Max Act: 8.2517. Min Act: -0.1700

Data Index: 6873 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 8.9704. Min Range: -8.9704

Max Act: 8.2829. Min Act: -0.1700

Data Index: 1076213 (C4 (Web Text))

Max Activating Token Index: 62

Text #18

Max Range: 8.9704. Min Range: -8.9704

Max Act: 8.0329. Min Act: -0.1700

Data Index: 95005 (C4 (Web Text))

Max Activating Token Index: 636

Text #19

Max Range: 8.9704. Min Range: -8.9704

Max Act: 8.1892. Min Act: -0.1700

Data Index: 401054 (C4 (Web Text))

Max Activating Token Index: 441