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

Dataset: Open Web Text

Neuron 1120 in Layer 6

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: 4.0556. Min Range: -4.0556

Max Act: 4.0556. Min Act: -0.1700

Data Index: 2691031 (Open Web Text)

Max Activating Token Index: 941

Text #1

Max Range: 4.0556. Min Range: -4.0556

Max Act: 4.0036. Min Act: -0.1700

Data Index: 4830790 (Open Web Text)

Max Activating Token Index: 875

Text #2

Max Range: 4.0556. Min Range: -4.0556

Max Act: 3.9913. Min Act: -0.1700

Data Index: 6708890 (Open Web Text)

Max Activating Token Index: 955

Text #3

Max Range: 4.0556. Min Range: -4.0556

Max Act: 3.9985. Min Act: -0.1700

Data Index: 7862371 (Open Web Text)

Max Activating Token Index: 784

Text #4

Max Range: 4.0556. Min Range: -4.0556

Max Act: 3.9426. Min Act: -0.1700

Data Index: 7516449 (Open Web Text)

Max Activating Token Index: 869

Text #5

Max Range: 4.0556. Min Range: -4.0556

Max Act: 3.9350. Min Act: -0.1700

Data Index: 5652201 (Open Web Text)

Max Activating Token Index: 358

Text #6

Max Range: 4.0556. Min Range: -4.0556

Max Act: 3.9219. Min Act: -0.1700

Data Index: 2586238 (Open Web Text)

Max Activating Token Index: 576

Text #7

Max Range: 4.0556. Min Range: -4.0556

Max Act: 3.9438. Min Act: -0.1700

Data Index: 1479523 (Open Web Text)

Max Activating Token Index: 649

Text #8

Max Range: 4.0556. Min Range: -4.0556

Max Act: 3.9302. Min Act: -0.1700

Data Index: 5433034 (Open Web Text)

Max Activating Token Index: 1019

Text #9

Max Range: 4.0556. Min Range: -4.0556

Max Act: 3.9175. Min Act: -0.1700

Data Index: 4771426 (Open Web Text)

Max Activating Token Index: 423

Text #10

Max Range: 4.0556. Min Range: -4.0556

Max Act: 3.9366. Min Act: -0.1700

Data Index: 2312912 (Open Web Text)

Max Activating Token Index: 723

Text #11

Max Range: 4.0556. Min Range: -4.0556

Max Act: 3.9093. Min Act: -0.1700

Data Index: 1485175 (Open Web Text)

Max Activating Token Index: 611

Text #12

Max Range: 4.0556. Min Range: -4.0556

Max Act: 3.9122. Min Act: -0.1700

Data Index: 435875 (Open Web Text)

Max Activating Token Index: 167

Text #13

Max Range: 4.0556. Min Range: -4.0556

Max Act: 3.9351. Min Act: -0.1700

Data Index: 2102049 (Open Web Text)

Max Activating Token Index: 888

Text #14

Max Range: 4.0556. Min Range: -4.0556

Max Act: 3.8954. Min Act: -0.1700

Data Index: 4471415 (Open Web Text)

Max Activating Token Index: 300

Text #15

Max Range: 4.0556. Min Range: -4.0556

Max Act: 3.9213. Min Act: -0.1700

Data Index: 6336642 (Open Web Text)

Max Activating Token Index: 439

Text #16

Max Range: 4.0556. Min Range: -4.0556

Max Act: 3.9168. Min Act: -0.1700

Data Index: 2662374 (Open Web Text)

Max Activating Token Index: 770

Text #17

Max Range: 4.0556. Min Range: -4.0556

Max Act: 3.8917. Min Act: -0.1700

Data Index: 2466845 (Open Web Text)

Max Activating Token Index: 842

Text #18

Max Range: 4.0556. Min Range: -4.0556

Max Act: 3.8880. Min Act: -0.1700

Data Index: 5302820 (Open Web Text)

Max Activating Token Index: 976

Text #19

Max Range: 4.0556. Min Range: -4.0556

Max Act: 3.9085. Min Act: -0.1700

Data Index: 2726387 (Open Web Text)

Max Activating Token Index: 34