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

Dataset: Open Web Text

Neuron 373 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: 4.2735. Min Range: -4.2735

Max Act: 4.2735. Min Act: -0.1700

Data Index: 7795821 (Open Web Text)

Max Activating Token Index: 552

Text #1

Max Range: 4.2735. Min Range: -4.2735

Max Act: 4.1144. Min Act: -0.1700

Data Index: 2248790 (Open Web Text)

Max Activating Token Index: 271

Text #2

Max Range: 4.2735. Min Range: -4.2735

Max Act: 4.1265. Min Act: -0.1700

Data Index: 7754284 (Open Web Text)

Max Activating Token Index: 184

Text #3

Max Range: 4.2735. Min Range: -4.2735

Max Act: 4.0894. Min Act: -0.1700

Data Index: 7458967 (Open Web Text)

Max Activating Token Index: 214

Text #4

Max Range: 4.2735. Min Range: -4.2735

Max Act: 4.1225. Min Act: -0.1700

Data Index: 1144043 (Open Web Text)

Max Activating Token Index: 197

Text #5

Max Range: 4.2735. Min Range: -4.2735

Max Act: 4.0669. Min Act: -0.1700

Data Index: 8173132 (Open Web Text)

Max Activating Token Index: 155

Text #6

Max Range: 4.2735. Min Range: -4.2735

Max Act: 4.0547. Min Act: -0.1700

Data Index: 6897169 (Open Web Text)

Max Activating Token Index: 468

Text #7

Max Range: 4.2735. Min Range: -4.2735

Max Act: 4.0243. Min Act: -0.1700

Data Index: 940157 (Open Web Text)

Max Activating Token Index: 622

Text #8

Max Range: 4.2735. Min Range: -4.2735

Max Act: 4.0727. Min Act: -0.1700

Data Index: 6975631 (Open Web Text)

Max Activating Token Index: 303

Text #9

Max Range: 4.2735. Min Range: -4.2735

Max Act: 4.0697. Min Act: -0.1700

Data Index: 5458214 (Open Web Text)

Max Activating Token Index: 466

Text #10

Max Range: 4.2735. Min Range: -4.2735

Max Act: 4.0019. Min Act: -0.1700

Data Index: 8155251 (Open Web Text)

Max Activating Token Index: 776

Text #11

Max Range: 4.2735. Min Range: -4.2735

Max Act: 4.0268. Min Act: -0.1700

Data Index: 655525 (Open Web Text)

Max Activating Token Index: 868

Text #12

Max Range: 4.2735. Min Range: -4.2735

Max Act: 4.0212. Min Act: -0.1700

Data Index: 288103 (Open Web Text)

Max Activating Token Index: 269

Text #13

Max Range: 4.2735. Min Range: -4.2735

Max Act: 4.0415. Min Act: -0.1700

Data Index: 1175012 (Open Web Text)

Max Activating Token Index: 364

Text #14

Max Range: 4.2735. Min Range: -4.2735

Max Act: 4.0392. Min Act: -0.1700

Data Index: 5433168 (Open Web Text)

Max Activating Token Index: 913

Text #15

Max Range: 4.2735. Min Range: -4.2735

Max Act: 4.0611. Min Act: -0.1700

Data Index: 8394731 (Open Web Text)

Max Activating Token Index: 246

Text #16

Max Range: 4.2735. Min Range: -4.2735

Max Act: 4.0073. Min Act: -0.1700

Data Index: 489033 (Open Web Text)

Max Activating Token Index: 1012

Text #17

Max Range: 4.2735. Min Range: -4.2735

Max Act: 4.0865. Min Act: -0.1700

Data Index: 8004067 (Open Web Text)

Max Activating Token Index: 372

Text #18

Max Range: 4.2735. Min Range: -4.2735

Max Act: 4.0127. Min Act: -0.1700

Data Index: 2771883 (Open Web Text)

Max Activating Token Index: 352

Text #19

Max Range: 4.2735. Min Range: -4.2735

Max Act: 3.9966. Min Act: -0.1700

Data Index: 5835397 (Open Web Text)

Max Activating Token Index: 918