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

Dataset: Open Web Text

Neuron 663 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: 3.1100. Min Range: -3.1100

Max Act: 3.1100. Min Act: -0.1700

Data Index: 4371133 (Open Web Text)

Max Activating Token Index: 243

Text #1

Max Range: 3.1100. Min Range: -3.1100

Max Act: 2.9956. Min Act: -0.1700

Data Index: 3519977 (Open Web Text)

Max Activating Token Index: 194

Text #2

Max Range: 3.1100. Min Range: -3.1100

Max Act: 2.9814. Min Act: -0.1700

Data Index: 5616834 (Open Web Text)

Max Activating Token Index: 127

Text #3

Max Range: 3.1100. Min Range: -3.1100

Max Act: 2.9766. Min Act: -0.1700

Data Index: 3402384 (Open Web Text)

Max Activating Token Index: 440

Text #4

Max Range: 3.1100. Min Range: -3.1100

Max Act: 2.9368. Min Act: -0.1700

Data Index: 2491762 (Open Web Text)

Max Activating Token Index: 808

Text #5

Max Range: 3.1100. Min Range: -3.1100

Max Act: 2.9292. Min Act: -0.1700

Data Index: 2362088 (Open Web Text)

Max Activating Token Index: 707

Text #6

Max Range: 3.1100. Min Range: -3.1100

Max Act: 2.9442. Min Act: -0.1700

Data Index: 2998883 (Open Web Text)

Max Activating Token Index: 1012

Text #7

Max Range: 3.1100. Min Range: -3.1100

Max Act: 2.9275. Min Act: -0.1700

Data Index: 2533637 (Open Web Text)

Max Activating Token Index: 237

Text #8

Max Range: 3.1100. Min Range: -3.1100

Max Act: 2.9467. Min Act: -0.1700

Data Index: 7575131 (Open Web Text)

Max Activating Token Index: 757

Text #9

Max Range: 3.1100. Min Range: -3.1100

Max Act: 2.9050. Min Act: -0.1700

Data Index: 1482304 (Open Web Text)

Max Activating Token Index: 204

Text #10

Max Range: 3.1100. Min Range: -3.1100

Max Act: 2.9047. Min Act: -0.1700

Data Index: 6039538 (Open Web Text)

Max Activating Token Index: 697

Text #11

Max Range: 3.1100. Min Range: -3.1100

Max Act: 2.8936. Min Act: -0.1700

Data Index: 3548032 (Open Web Text)

Max Activating Token Index: 137

Text #12

Max Range: 3.1100. Min Range: -3.1100

Max Act: 2.8795. Min Act: -0.1700

Data Index: 1640829 (Open Web Text)

Max Activating Token Index: 917

Text #13

Max Range: 3.1100. Min Range: -3.1100

Max Act: 2.8735. Min Act: -0.1700

Data Index: 4082272 (Open Web Text)

Max Activating Token Index: 714

Text #14

Max Range: 3.1100. Min Range: -3.1100

Max Act: 2.8978. Min Act: -0.1700

Data Index: 719698 (Open Web Text)

Max Activating Token Index: 41

Text #15

Max Range: 3.1100. Min Range: -3.1100

Max Act: 2.8746. Min Act: -0.1700

Data Index: 6564853 (Open Web Text)

Max Activating Token Index: 968

Text #16

Max Range: 3.1100. Min Range: -3.1100

Max Act: 2.8737. Min Act: -0.1700

Data Index: 6627244 (Open Web Text)

Max Activating Token Index: 430

Text #17

Max Range: 3.1100. Min Range: -3.1100

Max Act: 2.8643. Min Act: -0.1700

Data Index: 7020690 (Open Web Text)

Max Activating Token Index: 669

Text #18

Max Range: 3.1100. Min Range: -3.1100

Max Act: 2.8533. Min Act: -0.1700

Data Index: 4369516 (Open Web Text)

Max Activating Token Index: 604

Text #19

Max Range: 3.1100. Min Range: -3.1100

Max Act: 2.8666. Min Act: -0.1700

Data Index: 5691084 (Open Web Text)

Max Activating Token Index: 758