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

Dataset: Open Web Text

Neuron 1050 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: 3.1217. Min Range: -3.1217

Max Act: 3.1217. Min Act: -0.1700

Data Index: 5760254 (Open Web Text)

Max Activating Token Index: 444

Text #1

Max Range: 3.1217. Min Range: -3.1217

Max Act: 3.0789. Min Act: -0.1700

Data Index: 4410959 (Open Web Text)

Max Activating Token Index: 108

Text #2

Max Range: 3.1217. Min Range: -3.1217

Max Act: 3.0342. Min Act: -0.1700

Data Index: 3930403 (Open Web Text)

Max Activating Token Index: 131

Text #3

Max Range: 3.1217. Min Range: -3.1217

Max Act: 3.0153. Min Act: -0.1700

Data Index: 5970504 (Open Web Text)

Max Activating Token Index: 727

Text #4

Max Range: 3.1217. Min Range: -3.1217

Max Act: 2.9859. Min Act: -0.1700

Data Index: 5638311 (Open Web Text)

Max Activating Token Index: 841

Text #5

Max Range: 3.1217. Min Range: -3.1217

Max Act: 2.9686. Min Act: -0.1700

Data Index: 47877 (Open Web Text)

Max Activating Token Index: 313

Text #6

Max Range: 3.1217. Min Range: -3.1217

Max Act: 2.9462. Min Act: -0.1700

Data Index: 609941 (Open Web Text)

Max Activating Token Index: 352

Text #7

Max Range: 3.1217. Min Range: -3.1217

Max Act: 2.9402. Min Act: -0.1700

Data Index: 3799354 (Open Web Text)

Max Activating Token Index: 1004

Text #8

Max Range: 3.1217. Min Range: -3.1217

Max Act: 2.9481. Min Act: -0.1700

Data Index: 7630993 (Open Web Text)

Max Activating Token Index: 240

Text #9

Max Range: 3.1217. Min Range: -3.1217

Max Act: 2.9333. Min Act: -0.1700

Data Index: 8468207 (Open Web Text)

Max Activating Token Index: 83

Text #10

Max Range: 3.1217. Min Range: -3.1217

Max Act: 2.9236. Min Act: -0.1700

Data Index: 8659864 (Open Web Text)

Max Activating Token Index: 531

Text #11

Max Range: 3.1217. Min Range: -3.1217

Max Act: 2.9217. Min Act: -0.1700

Data Index: 2504671 (Open Web Text)

Max Activating Token Index: 382

Text #12

Max Range: 3.1217. Min Range: -3.1217

Max Act: 2.8909. Min Act: -0.1700

Data Index: 8316442 (Open Web Text)

Max Activating Token Index: 526

Text #13

Max Range: 3.1217. Min Range: -3.1217

Max Act: 2.8971. Min Act: -0.1700

Data Index: 8316446 (Open Web Text)

Max Activating Token Index: 321

Text #14

Max Range: 3.1217. Min Range: -3.1217

Max Act: 2.8856. Min Act: -0.1700

Data Index: 7607567 (Open Web Text)

Max Activating Token Index: 363

Text #15

Max Range: 3.1217. Min Range: -3.1217

Max Act: 2.9048. Min Act: -0.1700

Data Index: 8316439 (Open Web Text)

Max Activating Token Index: 542

Text #16

Max Range: 3.1217. Min Range: -3.1217

Max Act: 2.8859. Min Act: -0.1700

Data Index: 8659865 (Open Web Text)

Max Activating Token Index: 603

Text #17

Max Range: 3.1217. Min Range: -3.1217

Max Act: 2.8582. Min Act: -0.1700

Data Index: 3639029 (Open Web Text)

Max Activating Token Index: 139

Text #18

Max Range: 3.1217. Min Range: -3.1217

Max Act: 2.8465. Min Act: -0.1700

Data Index: 1143007 (Open Web Text)

Max Activating Token Index: 727

Text #19

Max Range: 3.1217. Min Range: -3.1217

Max Act: 2.8602. Min Act: -0.1700

Data Index: 4478861 (Open Web Text)

Max Activating Token Index: 994