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

Dataset: Open Web Text

Neuron 2455 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: 1.7917. Min Range: -1.7917

Max Act: 1.7820. Min Act: -0.1700

Data Index: 277416 (Open Web Text)

Max Activating Token Index: 23

Text #1

Max Range: 1.7917. Min Range: -1.7917

Max Act: 1.7917. Min Act: -0.1700

Data Index: 5229667 (Open Web Text)

Max Activating Token Index: 266

Text #2

Max Range: 1.7917. Min Range: -1.7917

Max Act: 1.7415. Min Act: -0.1700

Data Index: 533341 (Open Web Text)

Max Activating Token Index: 210

Text #3

Max Range: 1.7917. Min Range: -1.7917

Max Act: 1.7422. Min Act: -0.1700

Data Index: 6023819 (Open Web Text)

Max Activating Token Index: 116

Text #4

Max Range: 1.7917. Min Range: -1.7917

Max Act: 1.7268. Min Act: -0.1697

Data Index: 2232882 (Open Web Text)

Max Activating Token Index: 536

Text #5

Max Range: 1.7917. Min Range: -1.7917

Max Act: 1.7314. Min Act: -0.1700

Data Index: 4950495 (Open Web Text)

Max Activating Token Index: 674

Text #6

Max Range: 1.7917. Min Range: -1.7917

Max Act: 1.7214. Min Act: -0.1697

Data Index: 2630146 (Open Web Text)

Max Activating Token Index: 983

Text #7

Max Range: 1.7917. Min Range: -1.7917

Max Act: 1.7289. Min Act: -0.1700

Data Index: 795309 (Open Web Text)

Max Activating Token Index: 339

Text #8

Max Range: 1.7917. Min Range: -1.7917

Max Act: 1.7063. Min Act: -0.1700

Data Index: 2609713 (Open Web Text)

Max Activating Token Index: 214

Text #9

Max Range: 1.7917. Min Range: -1.7917

Max Act: 1.7117. Min Act: -0.1697

Data Index: 2630142 (Open Web Text)

Max Activating Token Index: 217

Text #10

Max Range: 1.7917. Min Range: -1.7917

Max Act: 1.7185. Min Act: -0.1700

Data Index: 5615020 (Open Web Text)

Max Activating Token Index: 69

Text #11

Max Range: 1.7917. Min Range: -1.7917

Max Act: 1.7139. Min Act: -0.1700

Data Index: 3390641 (Open Web Text)

Max Activating Token Index: 395

Text #12

Max Range: 1.7917. Min Range: -1.7917

Max Act: 1.7153. Min Act: -0.1700

Data Index: 5127012 (Open Web Text)

Max Activating Token Index: 354

Text #13

Max Range: 1.7917. Min Range: -1.7917

Max Act: 1.7155. Min Act: -0.1700

Data Index: 3841257 (Open Web Text)

Max Activating Token Index: 58

Text #14

Max Range: 1.7917. Min Range: -1.7917

Max Act: 1.7013. Min Act: -0.1700

Data Index: 213507 (Open Web Text)

Max Activating Token Index: 17

Text #15

Max Range: 1.7917. Min Range: -1.7917

Max Act: 1.7094. Min Act: -0.1700

Data Index: 8790368 (Open Web Text)

Max Activating Token Index: 312

Text #16

Max Range: 1.7917. Min Range: -1.7917

Max Act: 1.6958. Min Act: -0.1700

Data Index: 8669652 (Open Web Text)

Max Activating Token Index: 364

Text #17

Max Range: 1.7917. Min Range: -1.7917

Max Act: 1.7030. Min Act: -0.1699

Data Index: 2400600 (Open Web Text)

Max Activating Token Index: 531

Text #18

Max Range: 1.7917. Min Range: -1.7917

Max Act: 1.7075. Min Act: -0.1700

Data Index: 298454 (Open Web Text)

Max Activating Token Index: 413

Text #19

Max Range: 1.7917. Min Range: -1.7917

Max Act: 1.7066. Min Act: -0.1700

Data Index: 6435752 (Open Web Text)

Max Activating Token Index: 152