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

Dataset: Open Web Text

Neuron 2750 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: 5.4539. Min Range: -5.4539

Max Act: 5.4539. Min Act: -0.1700

Data Index: 8688373 (Open Web Text)

Max Activating Token Index: 480

Text #1

Max Range: 5.4539. Min Range: -5.4539

Max Act: 5.2505. Min Act: -0.1700

Data Index: 8688372 (Open Web Text)

Max Activating Token Index: 297

Text #2

Max Range: 5.4539. Min Range: -5.4539

Max Act: 5.2962. Min Act: -0.1700

Data Index: 1544415 (Open Web Text)

Max Activating Token Index: 474

Text #3

Max Range: 5.4539. Min Range: -5.4539

Max Act: 5.2335. Min Act: -0.1700

Data Index: 2166728 (Open Web Text)

Max Activating Token Index: 262

Text #4

Max Range: 5.4539. Min Range: -5.4539

Max Act: 5.0916. Min Act: -0.1700

Data Index: 1837067 (Open Web Text)

Max Activating Token Index: 284

Text #5

Max Range: 5.4539. Min Range: -5.4539

Max Act: 5.0647. Min Act: -0.1700

Data Index: 4180167 (Open Web Text)

Max Activating Token Index: 219

Text #6

Max Range: 5.4539. Min Range: -5.4539

Max Act: 5.0288. Min Act: -0.1700

Data Index: 2166727 (Open Web Text)

Max Activating Token Index: 487

Text #7

Max Range: 5.4539. Min Range: -5.4539

Max Act: 5.0265. Min Act: -0.1700

Data Index: 115418 (Open Web Text)

Max Activating Token Index: 109

Text #8

Max Range: 5.4539. Min Range: -5.4539

Max Act: 5.0215. Min Act: -0.1700

Data Index: 1544413 (Open Web Text)

Max Activating Token Index: 549

Text #9

Max Range: 5.4539. Min Range: -5.4539

Max Act: 4.8813. Min Act: -0.1700

Data Index: 8688376 (Open Web Text)

Max Activating Token Index: 382

Text #10

Max Range: 5.4539. Min Range: -5.4539

Max Act: 4.8776. Min Act: -0.1700

Data Index: 2166726 (Open Web Text)

Max Activating Token Index: 69

Text #11

Max Range: 5.4539. Min Range: -5.4539

Max Act: 4.8694. Min Act: -0.1700

Data Index: 7624751 (Open Web Text)

Max Activating Token Index: 636

Text #12

Max Range: 5.4539. Min Range: -5.4539

Max Act: 4.8109. Min Act: -0.1700

Data Index: 7624748 (Open Web Text)

Max Activating Token Index: 146

Text #13

Max Range: 5.4539. Min Range: -5.4539

Max Act: 4.8000. Min Act: -0.1700

Data Index: 6417847 (Open Web Text)

Max Activating Token Index: 973

Text #14

Max Range: 5.4539. Min Range: -5.4539

Max Act: 4.7646. Min Act: -0.1700

Data Index: 5806467 (Open Web Text)

Max Activating Token Index: 489

Text #15

Max Range: 5.4539. Min Range: -5.4539

Max Act: 4.7629. Min Act: -0.1700

Data Index: 4140256 (Open Web Text)

Max Activating Token Index: 738

Text #16

Max Range: 5.4539. Min Range: -5.4539

Max Act: 4.7208. Min Act: -0.1700

Data Index: 7978745 (Open Web Text)

Max Activating Token Index: 191

Text #17

Max Range: 5.4539. Min Range: -5.4539

Max Act: 4.6742. Min Act: -0.1700

Data Index: 2166723 (Open Web Text)

Max Activating Token Index: 446

Text #18

Max Range: 5.4539. Min Range: -5.4539

Max Act: 4.7053. Min Act: -0.1700

Data Index: 3744204 (Open Web Text)

Max Activating Token Index: 345

Text #19

Max Range: 5.4539. Min Range: -5.4539

Max Act: 4.6478. Min Act: -0.1700

Data Index: 4612336 (Open Web Text)

Max Activating Token Index: 973