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

Dataset: Open Web Text

Neuron 317 in Layer 5

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: 4.0762. Min Range: -4.0762

Max Act: 4.0762. Min Act: -0.1700

Data Index: 6710515 (Open Web Text)

Max Activating Token Index: 364

Text #1

Max Range: 4.0762. Min Range: -4.0762

Max Act: 4.0483. Min Act: -0.1700

Data Index: 4556885 (Open Web Text)

Max Activating Token Index: 271

Text #2

Max Range: 4.0762. Min Range: -4.0762

Max Act: 3.9575. Min Act: -0.1700

Data Index: 6291797 (Open Web Text)

Max Activating Token Index: 28

Text #3

Max Range: 4.0762. Min Range: -4.0762

Max Act: 3.9954. Min Act: -0.1700

Data Index: 8615138 (Open Web Text)

Max Activating Token Index: 9

Text #4

Max Range: 4.0762. Min Range: -4.0762

Max Act: 3.9659. Min Act: -0.1700

Data Index: 5141793 (Open Web Text)

Max Activating Token Index: 484

Text #5

Max Range: 4.0762. Min Range: -4.0762

Max Act: 3.9694. Min Act: -0.1700

Data Index: 2247525 (Open Web Text)

Max Activating Token Index: 71

Text #6

Max Range: 4.0762. Min Range: -4.0762

Max Act: 3.9410. Min Act: -0.1700

Data Index: 3605239 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 4.0762. Min Range: -4.0762

Max Act: 3.9395. Min Act: -0.1700

Data Index: 3367638 (Open Web Text)

Max Activating Token Index: 37

Text #8

Max Range: 4.0762. Min Range: -4.0762

Max Act: 3.9393. Min Act: -0.1700

Data Index: 5906698 (Open Web Text)

Max Activating Token Index: 661

Text #9

Max Range: 4.0762. Min Range: -4.0762

Max Act: 3.9185. Min Act: -0.1700

Data Index: 1994398 (Open Web Text)

Max Activating Token Index: 83

Text #10

Max Range: 4.0762. Min Range: -4.0762

Max Act: 3.8946. Min Act: -0.1700

Data Index: 5595914 (Open Web Text)

Max Activating Token Index: 870

Text #11

Max Range: 4.0762. Min Range: -4.0762

Max Act: 3.8734. Min Act: -0.1700

Data Index: 2175165 (Open Web Text)

Max Activating Token Index: 433

Text #12

Max Range: 4.0762. Min Range: -4.0762

Max Act: 3.8725. Min Act: -0.1700

Data Index: 4933267 (Open Web Text)

Max Activating Token Index: 36

Text #13

Max Range: 4.0762. Min Range: -4.0762

Max Act: 3.8972. Min Act: -0.1700

Data Index: 4589126 (Open Web Text)

Max Activating Token Index: 15

Text #14

Max Range: 4.0762. Min Range: -4.0762

Max Act: 3.8840. Min Act: -0.1700

Data Index: 6617978 (Open Web Text)

Max Activating Token Index: 122

Text #15

Max Range: 4.0762. Min Range: -4.0762

Max Act: 3.8808. Min Act: -0.1700

Data Index: 657634 (Open Web Text)

Max Activating Token Index: 945

Text #16

Max Range: 4.0762. Min Range: -4.0762

Max Act: 3.8718. Min Act: -0.1700

Data Index: 2062994 (Open Web Text)

Max Activating Token Index: 712

Text #17

Max Range: 4.0762. Min Range: -4.0762

Max Act: 3.8873. Min Act: -0.1700

Data Index: 8686397 (Open Web Text)

Max Activating Token Index: 98

Text #18

Max Range: 4.0762. Min Range: -4.0762

Max Act: 3.9088. Min Act: -0.1700

Data Index: 232657 (Open Web Text)

Max Activating Token Index: 478

Text #19

Max Range: 4.0762. Min Range: -4.0762

Max Act: 3.8866. Min Act: -0.1700

Data Index: 441625 (Open Web Text)

Max Activating Token Index: 819