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

Dataset: Open Web Text

Neuron 78 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: 3.3312. Min Range: -3.3312

Max Act: 3.3312. Min Act: -0.1700

Data Index: 6273227 (Open Web Text)

Max Activating Token Index: 493

Text #1

Max Range: 3.3312. Min Range: -3.3312

Max Act: 3.2103. Min Act: -0.1700

Data Index: 6948371 (Open Web Text)

Max Activating Token Index: 704

Text #2

Max Range: 3.3312. Min Range: -3.3312

Max Act: 3.2130. Min Act: -0.1700

Data Index: 4295626 (Open Web Text)

Max Activating Token Index: 521

Text #3

Max Range: 3.3312. Min Range: -3.3312

Max Act: 3.1829. Min Act: -0.1700

Data Index: 36650 (Open Web Text)

Max Activating Token Index: 883

Text #4

Max Range: 3.3312. Min Range: -3.3312

Max Act: 3.1751. Min Act: -0.1700

Data Index: 7485431 (Open Web Text)

Max Activating Token Index: 842

Text #5

Max Range: 3.3312. Min Range: -3.3312

Max Act: 3.1728. Min Act: -0.1700

Data Index: 6796977 (Open Web Text)

Max Activating Token Index: 258

Text #6

Max Range: 3.3312. Min Range: -3.3312

Max Act: 3.1674. Min Act: -0.1700

Data Index: 4973373 (Open Web Text)

Max Activating Token Index: 1020

Text #7

Max Range: 3.3312. Min Range: -3.3312

Max Act: 3.1746. Min Act: -0.1700

Data Index: 100651 (Open Web Text)

Max Activating Token Index: 438

Text #8

Max Range: 3.3312. Min Range: -3.3312

Max Act: 3.1514. Min Act: -0.1700

Data Index: 7265558 (Open Web Text)

Max Activating Token Index: 32

Text #9

Max Range: 3.3312. Min Range: -3.3312

Max Act: 3.1386. Min Act: -0.1700

Data Index: 7421019 (Open Web Text)

Max Activating Token Index: 820

Text #10

Max Range: 3.3312. Min Range: -3.3312

Max Act: 3.1496. Min Act: -0.1700

Data Index: 5422368 (Open Web Text)

Max Activating Token Index: 109

Text #11

Max Range: 3.3312. Min Range: -3.3312

Max Act: 3.1246. Min Act: -0.1700

Data Index: 1827460 (Open Web Text)

Max Activating Token Index: 151

Text #12

Max Range: 3.3312. Min Range: -3.3312

Max Act: 3.1265. Min Act: -0.1700

Data Index: 3299143 (Open Web Text)

Max Activating Token Index: 971

Text #13

Max Range: 3.3312. Min Range: -3.3312

Max Act: 3.1360. Min Act: -0.1700

Data Index: 4536696 (Open Web Text)

Max Activating Token Index: 288

Text #14

Max Range: 3.3312. Min Range: -3.3312

Max Act: 3.1056. Min Act: -0.1700

Data Index: 2113130 (Open Web Text)

Max Activating Token Index: 547

Text #15

Max Range: 3.3312. Min Range: -3.3312

Max Act: 3.0760. Min Act: -0.1700

Data Index: 920587 (Open Web Text)

Max Activating Token Index: 766

Text #16

Max Range: 3.3312. Min Range: -3.3312

Max Act: 3.0887. Min Act: -0.1700

Data Index: 4794460 (Open Web Text)

Max Activating Token Index: 413

Text #17

Max Range: 3.3312. Min Range: -3.3312

Max Act: 3.0839. Min Act: -0.1700

Data Index: 4385315 (Open Web Text)

Max Activating Token Index: 889

Text #18

Max Range: 3.3312. Min Range: -3.3312

Max Act: 3.0670. Min Act: -0.1700

Data Index: 3483938 (Open Web Text)

Max Activating Token Index: 889

Text #19

Max Range: 3.3312. Min Range: -3.3312

Max Act: 3.0534. Min Act: -0.1700

Data Index: 6769917 (Open Web Text)

Max Activating Token Index: 723