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

Dataset: Open Web Text

Neuron 1827 in Layer 4

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: 2.6608. Min Range: -2.6608

Max Act: 2.6608. Min Act: -0.1700

Data Index: 6574265 (Open Web Text)

Max Activating Token Index: 322

Text #1

Max Range: 2.6608. Min Range: -2.6608

Max Act: 2.5630. Min Act: -0.1700

Data Index: 4180349 (Open Web Text)

Max Activating Token Index: 188

Text #2

Max Range: 2.6608. Min Range: -2.6608

Max Act: 2.5665. Min Act: -0.1700

Data Index: 177396 (Open Web Text)

Max Activating Token Index: 735

Text #3

Max Range: 2.6608. Min Range: -2.6608

Max Act: 2.5136. Min Act: -0.1700

Data Index: 4823087 (Open Web Text)

Max Activating Token Index: 16

Text #4

Max Range: 2.6608. Min Range: -2.6608

Max Act: 2.4573. Min Act: -0.1700

Data Index: 6390100 (Open Web Text)

Max Activating Token Index: 588

Text #5

Max Range: 2.6608. Min Range: -2.6608

Max Act: 2.4613. Min Act: -0.1700

Data Index: 8054797 (Open Web Text)

Max Activating Token Index: 762

Text #6

Max Range: 2.6608. Min Range: -2.6608

Max Act: 2.4237. Min Act: -0.1700

Data Index: 6916989 (Open Web Text)

Max Activating Token Index: 544

Text #7

Max Range: 2.6608. Min Range: -2.6608

Max Act: 2.3806. Min Act: -0.1700

Data Index: 6742482 (Open Web Text)

Max Activating Token Index: 474

Text #8

Max Range: 2.6608. Min Range: -2.6608

Max Act: 2.4419. Min Act: -0.1700

Data Index: 8522709 (Open Web Text)

Max Activating Token Index: 718

Text #9

Max Range: 2.6608. Min Range: -2.6608

Max Act: 2.4327. Min Act: -0.1700

Data Index: 6155962 (Open Web Text)

Max Activating Token Index: 885

Text #10

Max Range: 2.6608. Min Range: -2.6608

Max Act: 2.3775. Min Act: -0.1700

Data Index: 4222722 (Open Web Text)

Max Activating Token Index: 885

Text #11

Max Range: 2.6608. Min Range: -2.6608

Max Act: 2.4672. Min Act: -0.1700

Data Index: 4480584 (Open Web Text)

Max Activating Token Index: 930

Text #12

Max Range: 2.6608. Min Range: -2.6608

Max Act: 2.3783. Min Act: -0.1700

Data Index: 4916611 (Open Web Text)

Max Activating Token Index: 411

Text #13

Max Range: 2.6608. Min Range: -2.6608

Max Act: 2.3946. Min Act: -0.1700

Data Index: 5913646 (Open Web Text)

Max Activating Token Index: 672

Text #14

Max Range: 2.6608. Min Range: -2.6608

Max Act: 2.3700. Min Act: -0.1700

Data Index: 3924701 (Open Web Text)

Max Activating Token Index: 8

Text #15

Max Range: 2.6608. Min Range: -2.6608

Max Act: 2.3933. Min Act: -0.1700

Data Index: 5665796 (Open Web Text)

Max Activating Token Index: 269

Text #16

Max Range: 2.6608. Min Range: -2.6608

Max Act: 2.3774. Min Act: -0.1700

Data Index: 2651109 (Open Web Text)

Max Activating Token Index: 322

Text #17

Max Range: 2.6608. Min Range: -2.6608

Max Act: 2.3901. Min Act: -0.1700

Data Index: 4092195 (Open Web Text)

Max Activating Token Index: 808

Text #18

Max Range: 2.6608. Min Range: -2.6608

Max Act: 2.4037. Min Act: -0.1700

Data Index: 8718813 (Open Web Text)

Max Activating Token Index: 837

Text #19

Max Range: 2.6608. Min Range: -2.6608

Max Act: 2.3519. Min Act: -0.1700

Data Index: 3632739 (Open Web Text)

Max Activating Token Index: 153