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

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

Neuron 992 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: 3.9544. Min Range: -3.9544

Max Act: 3.9544. Min Act: -0.1700

Data Index: 684316 (C4 (Web Text))

Max Activating Token Index: 615

Text #1

Max Range: 3.9544. Min Range: -3.9544

Max Act: 3.9231. Min Act: -0.1700

Data Index: 1062384 (C4 (Web Text))

Max Activating Token Index: 90

Text #2

Max Range: 3.9544. Min Range: -3.9544

Max Act: 3.9544. Min Act: -0.1700

Data Index: 1185837 (C4 (Web Text))

Max Activating Token Index: 10

Text #3

Max Range: 3.9544. Min Range: -3.9544

Max Act: 3.8605. Min Act: -0.1700

Data Index: 612349 (C4 (Web Text))

Max Activating Token Index: 527

Text #4

Max Range: 3.9544. Min Range: -3.9544

Max Act: 3.9231. Min Act: -0.1700

Data Index: 1092055 (C4 (Web Text))

Max Activating Token Index: 736

Text #5

Max Range: 3.9544. Min Range: -3.9544

Max Act: 3.8918. Min Act: -0.1700

Data Index: 891148 (C4 (Web Text))

Max Activating Token Index: 827

Text #6

Max Range: 3.9544. Min Range: -3.9544

Max Act: 3.8605. Min Act: -0.1700

Data Index: 781841 (C4 (Web Text))

Max Activating Token Index: 568

Text #7

Max Range: 3.9544. Min Range: -3.9544

Max Act: 3.8605. Min Act: -0.1700

Data Index: 706782 (C4 (Web Text))

Max Activating Token Index: 68

Text #8

Max Range: 3.9544. Min Range: -3.9544

Max Act: 3.8293. Min Act: -0.1700

Data Index: 1008424 (C4 (Web Text))

Max Activating Token Index: 656

Text #9

Max Range: 3.9544. Min Range: -3.9544

Max Act: 3.8293. Min Act: -0.1700

Data Index: 835794 (C4 (Web Text))

Max Activating Token Index: 11

Text #10

Max Range: 3.9544. Min Range: -3.9544

Max Act: 3.7980. Min Act: -0.1700

Data Index: 489227 (C4 (Web Text))

Max Activating Token Index: 998

Text #11

Max Range: 3.9544. Min Range: -3.9544

Max Act: 3.8293. Min Act: -0.1700

Data Index: 235841 (C4 (Web Text))

Max Activating Token Index: 157

Text #12

Max Range: 3.9544. Min Range: -3.9544

Max Act: 3.8293. Min Act: -0.1700

Data Index: 805507 (C4 (Web Text))

Max Activating Token Index: 474

Text #13

Max Range: 3.9544. Min Range: -3.9544

Max Act: 3.7667. Min Act: -0.1700

Data Index: 902819 (C4 (Web Text))

Max Activating Token Index: 3

Text #14

Max Range: 3.9544. Min Range: -3.9544

Max Act: 3.7667. Min Act: -0.1696

Data Index: 1236352 (C4 (Web Text))

Max Activating Token Index: 197

Text #15

Max Range: 3.9544. Min Range: -3.9544

Max Act: 3.7354. Min Act: -0.1700

Data Index: 227871 (C4 (Web Text))

Max Activating Token Index: 450

Text #16

Max Range: 3.9544. Min Range: -3.9544

Max Act: 3.7667. Min Act: -0.1700

Data Index: 632632 (C4 (Web Text))

Max Activating Token Index: 234

Text #17

Max Range: 3.9544. Min Range: -3.9544

Max Act: 3.7667. Min Act: -0.1700

Data Index: 710067 (C4 (Web Text))

Max Activating Token Index: 597

Text #18

Max Range: 3.9544. Min Range: -3.9544

Max Act: 3.7667. Min Act: -0.1700

Data Index: 15961 (C4 (Web Text))

Max Activating Token Index: 797

Text #19

Max Range: 3.9544. Min Range: -3.9544

Max Act: 3.7980. Min Act: -0.1700

Data Index: 37253 (C4 (Web Text))

Max Activating Token Index: 829