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

Dataset: Open Web Text

Neuron 675 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: 4.1381. Min Range: -4.1381

Max Act: 4.1381. Min Act: -0.1700

Data Index: 6607515 (Open Web Text)

Max Activating Token Index: 107

Text #1

Max Range: 4.1381. Min Range: -4.1381

Max Act: 4.1021. Min Act: -0.1700

Data Index: 6484277 (Open Web Text)

Max Activating Token Index: 774

Text #2

Max Range: 4.1381. Min Range: -4.1381

Max Act: 4.1232. Min Act: -0.1700

Data Index: 136523 (Open Web Text)

Max Activating Token Index: 537

Text #3

Max Range: 4.1381. Min Range: -4.1381

Max Act: 4.1328. Min Act: -0.1700

Data Index: 1203423 (Open Web Text)

Max Activating Token Index: 793

Text #4

Max Range: 4.1381. Min Range: -4.1381

Max Act: 4.1236. Min Act: -0.1700

Data Index: 227136 (Open Web Text)

Max Activating Token Index: 112

Text #5

Max Range: 4.1381. Min Range: -4.1381

Max Act: 4.0414. Min Act: -0.1700

Data Index: 2360022 (Open Web Text)

Max Activating Token Index: 278

Text #6

Max Range: 4.1381. Min Range: -4.1381

Max Act: 4.1019. Min Act: -0.1700

Data Index: 7109537 (Open Web Text)

Max Activating Token Index: 217

Text #7

Max Range: 4.1381. Min Range: -4.1381

Max Act: 4.1091. Min Act: -0.1700

Data Index: 2630444 (Open Web Text)

Max Activating Token Index: 557

Text #8

Max Range: 4.1381. Min Range: -4.1381

Max Act: 4.0875. Min Act: -0.1700

Data Index: 8787040 (Open Web Text)

Max Activating Token Index: 461

Text #9

Max Range: 4.1381. Min Range: -4.1381

Max Act: 4.0352. Min Act: -0.1700

Data Index: 1878687 (Open Web Text)

Max Activating Token Index: 993

Text #10

Max Range: 4.1381. Min Range: -4.1381

Max Act: 4.0637. Min Act: -0.1700

Data Index: 1469225 (Open Web Text)

Max Activating Token Index: 210

Text #11

Max Range: 4.1381. Min Range: -4.1381

Max Act: 4.0632. Min Act: -0.1700

Data Index: 6211343 (Open Web Text)

Max Activating Token Index: 387

Text #12

Max Range: 4.1381. Min Range: -4.1381

Max Act: 4.0284. Min Act: -0.1700

Data Index: 7704678 (Open Web Text)

Max Activating Token Index: 584

Text #13

Max Range: 4.1381. Min Range: -4.1381

Max Act: 4.0454. Min Act: -0.1700

Data Index: 5391601 (Open Web Text)

Max Activating Token Index: 252

Text #14

Max Range: 4.1381. Min Range: -4.1381

Max Act: 4.0527. Min Act: -0.1700

Data Index: 2058534 (Open Web Text)

Max Activating Token Index: 848

Text #15

Max Range: 4.1381. Min Range: -4.1381

Max Act: 4.0791. Min Act: -0.1700

Data Index: 2388780 (Open Web Text)

Max Activating Token Index: 579

Text #16

Max Range: 4.1381. Min Range: -4.1381

Max Act: 4.0114. Min Act: -0.1700

Data Index: 2907274 (Open Web Text)

Max Activating Token Index: 357

Text #17

Max Range: 4.1381. Min Range: -4.1381

Max Act: 4.0294. Min Act: -0.1700

Data Index: 6290134 (Open Web Text)

Max Activating Token Index: 573

Text #18

Max Range: 4.1381. Min Range: -4.1381

Max Act: 4.0268. Min Act: -0.1700

Data Index: 2275358 (Open Web Text)

Max Activating Token Index: 182

Text #19

Max Range: 4.1381. Min Range: -4.1381

Max Act: 4.0333. Min Act: -0.1700

Data Index: 4358254 (Open Web Text)

Max Activating Token Index: 597