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

Dataset: Open Web Text

Neuron 2675 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: 4.2095. Min Range: -4.2095

Max Act: 4.2095. Min Act: -0.1700

Data Index: 5833309 (Open Web Text)

Max Activating Token Index: 326

Text #1

Max Range: 4.2095. Min Range: -4.2095

Max Act: 4.1648. Min Act: -0.1700

Data Index: 2488484 (Open Web Text)

Max Activating Token Index: 867

Text #2

Max Range: 4.2095. Min Range: -4.2095

Max Act: 4.1178. Min Act: -0.1700

Data Index: 1156573 (Open Web Text)

Max Activating Token Index: 879

Text #3

Max Range: 4.2095. Min Range: -4.2095

Max Act: 4.0704. Min Act: -0.1700

Data Index: 5080610 (Open Web Text)

Max Activating Token Index: 429

Text #4

Max Range: 4.2095. Min Range: -4.2095

Max Act: 4.0492. Min Act: -0.1700

Data Index: 1518582 (Open Web Text)

Max Activating Token Index: 452

Text #5

Max Range: 4.2095. Min Range: -4.2095

Max Act: 4.0279. Min Act: -0.1700

Data Index: 5386156 (Open Web Text)

Max Activating Token Index: 809

Text #6

Max Range: 4.2095. Min Range: -4.2095

Max Act: 4.0524. Min Act: -0.1700

Data Index: 7515264 (Open Web Text)

Max Activating Token Index: 630

Text #7

Max Range: 4.2095. Min Range: -4.2095

Max Act: 3.9868. Min Act: -0.1700

Data Index: 3627631 (Open Web Text)

Max Activating Token Index: 370

Text #8

Max Range: 4.2095. Min Range: -4.2095

Max Act: 3.9904. Min Act: -0.1700

Data Index: 4628233 (Open Web Text)

Max Activating Token Index: 849

Text #9

Max Range: 4.2095. Min Range: -4.2095

Max Act: 3.9532. Min Act: -0.1700

Data Index: 2789136 (Open Web Text)

Max Activating Token Index: 520

Text #10

Max Range: 4.2095. Min Range: -4.2095

Max Act: 3.9628. Min Act: -0.1700

Data Index: 7273902 (Open Web Text)

Max Activating Token Index: 301

Text #11

Max Range: 4.2095. Min Range: -4.2095

Max Act: 3.9754. Min Act: -0.1700

Data Index: 5928137 (Open Web Text)

Max Activating Token Index: 678

Text #12

Max Range: 4.2095. Min Range: -4.2095

Max Act: 3.8827. Min Act: -0.1700

Data Index: 7253415 (Open Web Text)

Max Activating Token Index: 763

Text #13

Max Range: 4.2095. Min Range: -4.2095

Max Act: 3.9224. Min Act: -0.1700

Data Index: 9689 (Open Web Text)

Max Activating Token Index: 430

Text #14

Max Range: 4.2095. Min Range: -4.2095

Max Act: 3.8873. Min Act: -0.1700

Data Index: 3635483 (Open Web Text)

Max Activating Token Index: 847

Text #15

Max Range: 4.2095. Min Range: -4.2095

Max Act: 3.8968. Min Act: -0.1700

Data Index: 5544774 (Open Web Text)

Max Activating Token Index: 935

Text #16

Max Range: 4.2095. Min Range: -4.2095

Max Act: 3.8929. Min Act: -0.1700

Data Index: 439704 (Open Web Text)

Max Activating Token Index: 116

Text #17

Max Range: 4.2095. Min Range: -4.2095

Max Act: 3.9380. Min Act: -0.1700

Data Index: 7915293 (Open Web Text)

Max Activating Token Index: 498

Text #18

Max Range: 4.2095. Min Range: -4.2095

Max Act: 3.9207. Min Act: -0.1700

Data Index: 764510 (Open Web Text)

Max Activating Token Index: 338

Text #19

Max Range: 4.2095. Min Range: -4.2095

Max Act: 3.9156. Min Act: -0.1700

Data Index: 1602069 (Open Web Text)

Max Activating Token Index: 782