Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 176 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 1.6353. Min Range: -1.6353

Max Act: 1.6353. Min Act: -0.1700

Data Index: 2673780 (Open Web Text)

Max Activating Token Index: 217

Text #1

Max Range: 1.6353. Min Range: -1.6353

Max Act: 1.6231. Min Act: -0.1700

Data Index: 3736669 (Open Web Text)

Max Activating Token Index: 914

Text #2

Max Range: 1.6353. Min Range: -1.6353

Max Act: 1.6094. Min Act: -0.1700

Data Index: 6202292 (Open Web Text)

Max Activating Token Index: 611

Text #3

Max Range: 1.6353. Min Range: -1.6353

Max Act: 1.6002. Min Act: -0.1700

Data Index: 6825730 (Open Web Text)

Max Activating Token Index: 522

Text #4

Max Range: 1.6353. Min Range: -1.6353

Max Act: 1.5959. Min Act: -0.1700

Data Index: 6774044 (Open Web Text)

Max Activating Token Index: 28

Text #5

Max Range: 1.6353. Min Range: -1.6353

Max Act: 1.5951. Min Act: -0.1700

Data Index: 6095967 (Open Web Text)

Max Activating Token Index: 74

Text #6

Max Range: 1.6353. Min Range: -1.6353

Max Act: 1.5806. Min Act: -0.1697

Data Index: 7452529 (Open Web Text)

Max Activating Token Index: 908

Text #7

Max Range: 1.6353. Min Range: -1.6353

Max Act: 1.5825. Min Act: -0.1700

Data Index: 2893560 (Open Web Text)

Max Activating Token Index: 783

Text #8

Max Range: 1.6353. Min Range: -1.6353

Max Act: 1.5763. Min Act: -0.1700

Data Index: 4482694 (Open Web Text)

Max Activating Token Index: 972

Text #9

Max Range: 1.6353. Min Range: -1.6353

Max Act: 1.5767. Min Act: -0.1700

Data Index: 1059521 (Open Web Text)

Max Activating Token Index: 580

Text #10

Max Range: 1.6353. Min Range: -1.6353

Max Act: 1.5729. Min Act: -0.1700

Data Index: 4482695 (Open Web Text)

Max Activating Token Index: 211

Text #11

Max Range: 1.6353. Min Range: -1.6353

Max Act: 1.5729. Min Act: -0.1700

Data Index: 7293767 (Open Web Text)

Max Activating Token Index: 120

Text #12

Max Range: 1.6353. Min Range: -1.6353

Max Act: 1.5575. Min Act: -0.1700

Data Index: 6329857 (Open Web Text)

Max Activating Token Index: 833

Text #13

Max Range: 1.6353. Min Range: -1.6353

Max Act: 1.5585. Min Act: -0.1699

Data Index: 7311967 (Open Web Text)

Max Activating Token Index: 24

Text #14

Max Range: 1.6353. Min Range: -1.6353

Max Act: 1.5678. Min Act: -0.1700

Data Index: 5124851 (Open Web Text)

Max Activating Token Index: 192

Text #15

Max Range: 1.6353. Min Range: -1.6353

Max Act: 1.5608. Min Act: -0.1699

Data Index: 8001451 (Open Web Text)

Max Activating Token Index: 836

Text #16

Max Range: 1.6353. Min Range: -1.6353

Max Act: 1.5543. Min Act: -0.1700

Data Index: 5910258 (Open Web Text)

Max Activating Token Index: 26

Text #17

Max Range: 1.6353. Min Range: -1.6353

Max Act: 1.5554. Min Act: -0.1700

Data Index: 310920 (Open Web Text)

Max Activating Token Index: 518

Text #18

Max Range: 1.6353. Min Range: -1.6353

Max Act: 1.5502. Min Act: -0.1700

Data Index: 3998054 (Open Web Text)

Max Activating Token Index: 70

Text #19

Max Range: 1.6353. Min Range: -1.6353

Max Act: 1.5585. Min Act: -0.1699

Data Index: 1799801 (Open Web Text)

Max Activating Token Index: 146