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

Dataset: Open Web Text

Neuron 1578 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: 1.7049. Min Range: -1.7049

Max Act: 1.7049. Min Act: -0.1700

Data Index: 3613729 (Open Web Text)

Max Activating Token Index: 561

Text #1

Max Range: 1.7049. Min Range: -1.7049

Max Act: 1.6703. Min Act: -0.1700

Data Index: 8376252 (Open Web Text)

Max Activating Token Index: 320

Text #2

Max Range: 1.7049. Min Range: -1.7049

Max Act: 1.6527. Min Act: -0.1700

Data Index: 7379444 (Open Web Text)

Max Activating Token Index: 346

Text #3

Max Range: 1.7049. Min Range: -1.7049

Max Act: 1.6385. Min Act: -0.1700

Data Index: 4664914 (Open Web Text)

Max Activating Token Index: 382

Text #4

Max Range: 1.7049. Min Range: -1.7049

Max Act: 1.6454. Min Act: -0.1700

Data Index: 5975684 (Open Web Text)

Max Activating Token Index: 492

Text #5

Max Range: 1.7049. Min Range: -1.7049

Max Act: 1.6418. Min Act: -0.1700

Data Index: 4984036 (Open Web Text)

Max Activating Token Index: 894

Text #6

Max Range: 1.7049. Min Range: -1.7049

Max Act: 1.6461. Min Act: -0.1700

Data Index: 8162393 (Open Web Text)

Max Activating Token Index: 329

Text #7

Max Range: 1.7049. Min Range: -1.7049

Max Act: 1.6188. Min Act: -0.1700

Data Index: 696822 (Open Web Text)

Max Activating Token Index: 311

Text #8

Max Range: 1.7049. Min Range: -1.7049

Max Act: 1.6264. Min Act: -0.1700

Data Index: 2815640 (Open Web Text)

Max Activating Token Index: 229

Text #9

Max Range: 1.7049. Min Range: -1.7049

Max Act: 1.6268. Min Act: -0.1700

Data Index: 2188513 (Open Web Text)

Max Activating Token Index: 752

Text #10

Max Range: 1.7049. Min Range: -1.7049

Max Act: 1.6167. Min Act: -0.1700

Data Index: 2965707 (Open Web Text)

Max Activating Token Index: 411

Text #11

Max Range: 1.7049. Min Range: -1.7049

Max Act: 1.6044. Min Act: -0.1700

Data Index: 775457 (Open Web Text)

Max Activating Token Index: 962

Text #12

Max Range: 1.7049. Min Range: -1.7049

Max Act: 1.6194. Min Act: -0.1700

Data Index: 31112 (Open Web Text)

Max Activating Token Index: 661

Text #13

Max Range: 1.7049. Min Range: -1.7049

Max Act: 1.6116. Min Act: -0.1700

Data Index: 4913356 (Open Web Text)

Max Activating Token Index: 436

Text #14

Max Range: 1.7049. Min Range: -1.7049

Max Act: 1.6090. Min Act: -0.1700

Data Index: 5386352 (Open Web Text)

Max Activating Token Index: 547

Text #15

Max Range: 1.7049. Min Range: -1.7049

Max Act: 1.6090. Min Act: -0.1700

Data Index: 3775915 (Open Web Text)

Max Activating Token Index: 768

Text #16

Max Range: 1.7049. Min Range: -1.7049

Max Act: 1.6081. Min Act: -0.1700

Data Index: 6357968 (Open Web Text)

Max Activating Token Index: 673

Text #17

Max Range: 1.7049. Min Range: -1.7049

Max Act: 1.6121. Min Act: -0.1700

Data Index: 2918514 (Open Web Text)

Max Activating Token Index: 123

Text #18

Max Range: 1.7049. Min Range: -1.7049

Max Act: 1.6065. Min Act: -0.1700

Data Index: 1758009 (Open Web Text)

Max Activating Token Index: 633

Text #19

Max Range: 1.7049. Min Range: -1.7049

Max Act: 1.6071. Min Act: -0.1700

Data Index: 4669797 (Open Web Text)

Max Activating Token Index: 476