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

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

Neuron 915 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.9553. Min Range: -7.9553

Max Act: 7.7678. Min Act: -0.1700

Data Index: 133013 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 7.9553. Min Range: -7.9553

Max Act: 7.7678. Min Act: -0.1700

Data Index: 241929 (C4 (Web Text))

Max Activating Token Index: 156

Text #2

Max Range: 7.9553. Min Range: -7.9553

Max Act: 7.6428. Min Act: -0.1700

Data Index: 279496 (C4 (Web Text))

Max Activating Token Index: 321

Text #3

Max Range: 7.9553. Min Range: -7.9553

Max Act: 7.9553. Min Act: -0.1700

Data Index: 912659 (C4 (Web Text))

Max Activating Token Index: 215

Text #4

Max Range: 7.9553. Min Range: -7.9553

Max Act: 7.7053. Min Act: -0.1700

Data Index: 12140 (C4 (Web Text))

Max Activating Token Index: 187

Text #5

Max Range: 7.9553. Min Range: -7.9553

Max Act: 7.5803. Min Act: -0.1700

Data Index: 107149 (C4 (Web Text))

Max Activating Token Index: 779

Text #6

Max Range: 7.9553. Min Range: -7.9553

Max Act: 7.7678. Min Act: -0.1700

Data Index: 433214 (C4 (Web Text))

Max Activating Token Index: 884

Text #7

Max Range: 7.9553. Min Range: -7.9553

Max Act: 7.5178. Min Act: -0.1700

Data Index: 669862 (C4 (Web Text))

Max Activating Token Index: 256

Text #8

Max Range: 7.9553. Min Range: -7.9553

Max Act: 7.7678. Min Act: -0.1699

Data Index: 705325 (C4 (Web Text))

Max Activating Token Index: 900

Text #9

Max Range: 7.9553. Min Range: -7.9553

Max Act: 7.6428. Min Act: -0.1700

Data Index: 285038 (C4 (Web Text))

Max Activating Token Index: 350

Text #10

Max Range: 7.9553. Min Range: -7.9553

Max Act: 7.7678. Min Act: -0.1700

Data Index: 91577 (C4 (Web Text))

Max Activating Token Index: 1008

Text #11

Max Range: 7.9553. Min Range: -7.9553

Max Act: 7.6428. Min Act: -0.1700

Data Index: 881766 (C4 (Web Text))

Max Activating Token Index: 395

Text #12

Max Range: 7.9553. Min Range: -7.9553

Max Act: 7.5803. Min Act: -0.1700

Data Index: 446091 (C4 (Web Text))

Max Activating Token Index: 993

Text #13

Max Range: 7.9553. Min Range: -7.9553

Max Act: 7.6428. Min Act: -0.1700

Data Index: 567121 (C4 (Web Text))

Max Activating Token Index: 899

Text #14

Max Range: 7.9553. Min Range: -7.9553

Max Act: 7.7053. Min Act: -0.1700

Data Index: 209608 (C4 (Web Text))

Max Activating Token Index: 304

Text #15

Max Range: 7.9553. Min Range: -7.9553

Max Act: 7.4553. Min Act: -0.1700

Data Index: 639079 (C4 (Web Text))

Max Activating Token Index: 785

Text #16

Max Range: 7.9553. Min Range: -7.9553

Max Act: 7.7053. Min Act: -0.1700

Data Index: 178493 (C4 (Web Text))

Max Activating Token Index: 356

Text #17

Max Range: 7.9553. Min Range: -7.9553

Max Act: 7.7678. Min Act: -0.1700

Data Index: 148818 (C4 (Web Text))

Max Activating Token Index: 147

Text #18

Max Range: 7.9553. Min Range: -7.9553

Max Act: 7.7678. Min Act: -0.1700

Data Index: 909534 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 7.9553. Min Range: -7.9553

Max Act: 7.5803. Min Act: -0.1699

Data Index: 1034818 (C4 (Web Text))

Max Activating Token Index: 774