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

Dataset: Open Web Text

Neuron 2638 in Layer 5

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: 5.5224. Min Range: -5.5224

Max Act: 5.4717. Min Act: -0.1700

Data Index: 6854819 (Open Web Text)

Max Activating Token Index: 920

Text #1

Max Range: 5.5224. Min Range: -5.5224

Max Act: 5.5224. Min Act: -0.1700

Data Index: 6938834 (Open Web Text)

Max Activating Token Index: 280

Text #2

Max Range: 5.5224. Min Range: -5.5224

Max Act: 5.4251. Min Act: -0.1700

Data Index: 7132105 (Open Web Text)

Max Activating Token Index: 278

Text #3

Max Range: 5.5224. Min Range: -5.5224

Max Act: 5.4575. Min Act: -0.1700

Data Index: 1976750 (Open Web Text)

Max Activating Token Index: 932

Text #4

Max Range: 5.5224. Min Range: -5.5224

Max Act: 5.3510. Min Act: -0.1700

Data Index: 8522166 (Open Web Text)

Max Activating Token Index: 600

Text #5

Max Range: 5.5224. Min Range: -5.5224

Max Act: 5.3618. Min Act: -0.1700

Data Index: 7510618 (Open Web Text)

Max Activating Token Index: 369

Text #6

Max Range: 5.5224. Min Range: -5.5224

Max Act: 5.3106. Min Act: -0.1700

Data Index: 8662294 (Open Web Text)

Max Activating Token Index: 637

Text #7

Max Range: 5.5224. Min Range: -5.5224

Max Act: 5.2538. Min Act: -0.1700

Data Index: 6587749 (Open Web Text)

Max Activating Token Index: 576

Text #8

Max Range: 5.5224. Min Range: -5.5224

Max Act: 5.3320. Min Act: -0.1700

Data Index: 2144961 (Open Web Text)

Max Activating Token Index: 1003

Text #9

Max Range: 5.5224. Min Range: -5.5224

Max Act: 5.3231. Min Act: -0.1700

Data Index: 7676006 (Open Web Text)

Max Activating Token Index: 493

Text #10

Max Range: 5.5224. Min Range: -5.5224

Max Act: 5.3007. Min Act: -0.1700

Data Index: 6961578 (Open Web Text)

Max Activating Token Index: 685

Text #11

Max Range: 5.5224. Min Range: -5.5224

Max Act: 5.3238. Min Act: -0.1700

Data Index: 5351744 (Open Web Text)

Max Activating Token Index: 448

Text #12

Max Range: 5.5224. Min Range: -5.5224

Max Act: 5.1815. Min Act: -0.1700

Data Index: 1524742 (Open Web Text)

Max Activating Token Index: 442

Text #13

Max Range: 5.5224. Min Range: -5.5224

Max Act: 5.2267. Min Act: -0.1700

Data Index: 8031460 (Open Web Text)

Max Activating Token Index: 515

Text #14

Max Range: 5.5224. Min Range: -5.5224

Max Act: 5.2127. Min Act: -0.1700

Data Index: 8184346 (Open Web Text)

Max Activating Token Index: 445

Text #15

Max Range: 5.5224. Min Range: -5.5224

Max Act: 5.2334. Min Act: -0.1700

Data Index: 5275483 (Open Web Text)

Max Activating Token Index: 392

Text #16

Max Range: 5.5224. Min Range: -5.5224

Max Act: 5.2350. Min Act: -0.1700

Data Index: 6895034 (Open Web Text)

Max Activating Token Index: 448

Text #17

Max Range: 5.5224. Min Range: -5.5224

Max Act: 5.2018. Min Act: -0.1700

Data Index: 2767519 (Open Web Text)

Max Activating Token Index: 228

Text #18

Max Range: 5.5224. Min Range: -5.5224

Max Act: 5.1867. Min Act: -0.1700

Data Index: 6484822 (Open Web Text)

Max Activating Token Index: 998

Text #19

Max Range: 5.5224. Min Range: -5.5224

Max Act: 5.1916. Min Act: -0.1700

Data Index: 6503208 (Open Web Text)

Max Activating Token Index: 875