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

Dataset: Open Web Text

Neuron 730 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: 3.1181. Min Range: -3.1181

Max Act: 3.1181. Min Act: -0.1700

Data Index: 1685171 (Open Web Text)

Max Activating Token Index: 158

Text #1

Max Range: 3.1181. Min Range: -3.1181

Max Act: 3.1083. Min Act: -0.1700

Data Index: 2220729 (Open Web Text)

Max Activating Token Index: 227

Text #2

Max Range: 3.1181. Min Range: -3.1181

Max Act: 3.0744. Min Act: -0.1700

Data Index: 2452258 (Open Web Text)

Max Activating Token Index: 966

Text #3

Max Range: 3.1181. Min Range: -3.1181

Max Act: 3.0693. Min Act: -0.1700

Data Index: 6432946 (Open Web Text)

Max Activating Token Index: 202

Text #4

Max Range: 3.1181. Min Range: -3.1181

Max Act: 3.0702. Min Act: -0.1700

Data Index: 6711527 (Open Web Text)

Max Activating Token Index: 725

Text #5

Max Range: 3.1181. Min Range: -3.1181

Max Act: 2.9718. Min Act: -0.1700

Data Index: 8565991 (Open Web Text)

Max Activating Token Index: 627

Text #6

Max Range: 3.1181. Min Range: -3.1181

Max Act: 2.9771. Min Act: -0.1700

Data Index: 6182554 (Open Web Text)

Max Activating Token Index: 855

Text #7

Max Range: 3.1181. Min Range: -3.1181

Max Act: 2.9684. Min Act: -0.1700

Data Index: 4157047 (Open Web Text)

Max Activating Token Index: 816

Text #8

Max Range: 3.1181. Min Range: -3.1181

Max Act: 2.9469. Min Act: -0.1700

Data Index: 713737 (Open Web Text)

Max Activating Token Index: 973

Text #9

Max Range: 3.1181. Min Range: -3.1181

Max Act: 2.9804. Min Act: -0.1700

Data Index: 8726373 (Open Web Text)

Max Activating Token Index: 854

Text #10

Max Range: 3.1181. Min Range: -3.1181

Max Act: 2.9590. Min Act: -0.1700

Data Index: 1850013 (Open Web Text)

Max Activating Token Index: 905

Text #11

Max Range: 3.1181. Min Range: -3.1181

Max Act: 2.9399. Min Act: -0.1700

Data Index: 1418675 (Open Web Text)

Max Activating Token Index: 468

Text #12

Max Range: 3.1181. Min Range: -3.1181

Max Act: 2.9195. Min Act: -0.1700

Data Index: 2586386 (Open Web Text)

Max Activating Token Index: 80

Text #13

Max Range: 3.1181. Min Range: -3.1181

Max Act: 2.9320. Min Act: -0.1700

Data Index: 5863598 (Open Web Text)

Max Activating Token Index: 804

Text #14

Max Range: 3.1181. Min Range: -3.1181

Max Act: 2.9077. Min Act: -0.1700

Data Index: 2506792 (Open Web Text)

Max Activating Token Index: 499

Text #15

Max Range: 3.1181. Min Range: -3.1181

Max Act: 2.9200. Min Act: -0.1700

Data Index: 292660 (Open Web Text)

Max Activating Token Index: 525

Text #16

Max Range: 3.1181. Min Range: -3.1181

Max Act: 2.9034. Min Act: -0.1700

Data Index: 4127442 (Open Web Text)

Max Activating Token Index: 306

Text #17

Max Range: 3.1181. Min Range: -3.1181

Max Act: 2.9128. Min Act: -0.1700

Data Index: 4718260 (Open Web Text)

Max Activating Token Index: 926

Text #18

Max Range: 3.1181. Min Range: -3.1181

Max Act: 2.8999. Min Act: -0.1700

Data Index: 729523 (Open Web Text)

Max Activating Token Index: 771

Text #19

Max Range: 3.1181. Min Range: -3.1181

Max Act: 2.9138. Min Act: -0.1700

Data Index: 322788 (Open Web Text)

Max Activating Token Index: 763