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

Dataset: Open Web Text

Neuron 970 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: 7.1812. Min Range: -7.1812

Max Act: 7.1812. Min Act: -0.1700

Data Index: 1208087 (Open Web Text)

Max Activating Token Index: 182

Text #1

Max Range: 7.1812. Min Range: -7.1812

Max Act: 7.1349. Min Act: -0.1700

Data Index: 349548 (Open Web Text)

Max Activating Token Index: 340

Text #2

Max Range: 7.1812. Min Range: -7.1812

Max Act: 7.1276. Min Act: -0.1700

Data Index: 7442734 (Open Web Text)

Max Activating Token Index: 156

Text #3

Max Range: 7.1812. Min Range: -7.1812

Max Act: 7.1202. Min Act: -0.1700

Data Index: 5494089 (Open Web Text)

Max Activating Token Index: 245

Text #4

Max Range: 7.1812. Min Range: -7.1812

Max Act: 7.0648. Min Act: -0.1700

Data Index: 8113494 (Open Web Text)

Max Activating Token Index: 73

Text #5

Max Range: 7.1812. Min Range: -7.1812

Max Act: 7.1020. Min Act: -0.1700

Data Index: 5772203 (Open Web Text)

Max Activating Token Index: 202

Text #6

Max Range: 7.1812. Min Range: -7.1812

Max Act: 7.0896. Min Act: -0.1700

Data Index: 5740590 (Open Web Text)

Max Activating Token Index: 664

Text #7

Max Range: 7.1812. Min Range: -7.1812

Max Act: 7.0802. Min Act: -0.1700

Data Index: 3775796 (Open Web Text)

Max Activating Token Index: 238

Text #8

Max Range: 7.1812. Min Range: -7.1812

Max Act: 7.0594. Min Act: -0.1700

Data Index: 3665477 (Open Web Text)

Max Activating Token Index: 637

Text #9

Max Range: 7.1812. Min Range: -7.1812

Max Act: 7.0525. Min Act: -0.1700

Data Index: 4160211 (Open Web Text)

Max Activating Token Index: 17

Text #10

Max Range: 7.1812. Min Range: -7.1812

Max Act: 7.0369. Min Act: -0.1700

Data Index: 8637978 (Open Web Text)

Max Activating Token Index: 165

Text #11

Max Range: 7.1812. Min Range: -7.1812

Max Act: 7.0214. Min Act: -0.1700

Data Index: 6931238 (Open Web Text)

Max Activating Token Index: 766

Text #12

Max Range: 7.1812. Min Range: -7.1812

Max Act: 7.0447. Min Act: -0.1700

Data Index: 4568978 (Open Web Text)

Max Activating Token Index: 569

Text #13

Max Range: 7.1812. Min Range: -7.1812

Max Act: 7.0288. Min Act: -0.1700

Data Index: 2387496 (Open Web Text)

Max Activating Token Index: 81

Text #14

Max Range: 7.1812. Min Range: -7.1812

Max Act: 7.0438. Min Act: -0.1700

Data Index: 3481210 (Open Web Text)

Max Activating Token Index: 785

Text #15

Max Range: 7.1812. Min Range: -7.1812

Max Act: 7.0427. Min Act: -0.1700

Data Index: 232035 (Open Web Text)

Max Activating Token Index: 236

Text #16

Max Range: 7.1812. Min Range: -7.1812

Max Act: 6.9901. Min Act: -0.1700

Data Index: 3165838 (Open Web Text)

Max Activating Token Index: 608

Text #17

Max Range: 7.1812. Min Range: -7.1812

Max Act: 7.0057. Min Act: -0.1700

Data Index: 4870607 (Open Web Text)

Max Activating Token Index: 252

Text #18

Max Range: 7.1812. Min Range: -7.1812

Max Act: 6.9963. Min Act: -0.1700

Data Index: 869129 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 7.1812. Min Range: -7.1812

Max Act: 6.9838. Min Act: -0.1700

Data Index: 7061281 (Open Web Text)

Max Activating Token Index: 25