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

Dataset: Open Web Text

Neuron 2507 in Layer 3

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: 3.5122. Min Range: -3.5122

Max Act: 3.5122. Min Act: -0.1700

Data Index: 6348273 (Open Web Text)

Max Activating Token Index: 406

Text #1

Max Range: 3.5122. Min Range: -3.5122

Max Act: 3.4831. Min Act: -0.1700

Data Index: 2011065 (Open Web Text)

Max Activating Token Index: 434

Text #2

Max Range: 3.5122. Min Range: -3.5122

Max Act: 3.4851. Min Act: -0.1700

Data Index: 6068176 (Open Web Text)

Max Activating Token Index: 325

Text #3

Max Range: 3.5122. Min Range: -3.5122

Max Act: 3.4970. Min Act: -0.1700

Data Index: 8802813 (Open Web Text)

Max Activating Token Index: 20

Text #4

Max Range: 3.5122. Min Range: -3.5122

Max Act: 3.4786. Min Act: -0.1700

Data Index: 5803269 (Open Web Text)

Max Activating Token Index: 461

Text #5

Max Range: 3.5122. Min Range: -3.5122

Max Act: 3.4638. Min Act: -0.1700

Data Index: 8082921 (Open Web Text)

Max Activating Token Index: 827

Text #6

Max Range: 3.5122. Min Range: -3.5122

Max Act: 3.4518. Min Act: -0.1700

Data Index: 4643766 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 3.5122. Min Range: -3.5122

Max Act: 3.4221. Min Act: -0.1700

Data Index: 5584918 (Open Web Text)

Max Activating Token Index: 212

Text #8

Max Range: 3.5122. Min Range: -3.5122

Max Act: 3.4502. Min Act: -0.1700

Data Index: 8231386 (Open Web Text)

Max Activating Token Index: 973

Text #9

Max Range: 3.5122. Min Range: -3.5122

Max Act: 3.4469. Min Act: -0.1700

Data Index: 7467341 (Open Web Text)

Max Activating Token Index: 422

Text #10

Max Range: 3.5122. Min Range: -3.5122

Max Act: 3.4389. Min Act: -0.1700

Data Index: 4965418 (Open Web Text)

Max Activating Token Index: 19

Text #11

Max Range: 3.5122. Min Range: -3.5122

Max Act: 3.4287. Min Act: -0.1700

Data Index: 5221374 (Open Web Text)

Max Activating Token Index: 439

Text #12

Max Range: 3.5122. Min Range: -3.5122

Max Act: 3.4485. Min Act: -0.1700

Data Index: 5307617 (Open Web Text)

Max Activating Token Index: 575

Text #13

Max Range: 3.5122. Min Range: -3.5122

Max Act: 3.4414. Min Act: -0.1700

Data Index: 8090662 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 3.5122. Min Range: -3.5122

Max Act: 3.4087. Min Act: -0.1700

Data Index: 1454487 (Open Web Text)

Max Activating Token Index: 41

Text #15

Max Range: 3.5122. Min Range: -3.5122

Max Act: 3.4290. Min Act: -0.1700

Data Index: 1621735 (Open Web Text)

Max Activating Token Index: 709

Text #16

Max Range: 3.5122. Min Range: -3.5122

Max Act: 3.4238. Min Act: -0.1700

Data Index: 3355386 (Open Web Text)

Max Activating Token Index: 16

Text #17

Max Range: 3.5122. Min Range: -3.5122

Max Act: 3.4242. Min Act: -0.1700

Data Index: 6857270 (Open Web Text)

Max Activating Token Index: 504

Text #18

Max Range: 3.5122. Min Range: -3.5122

Max Act: 3.4102. Min Act: -0.1700

Data Index: 2725679 (Open Web Text)

Max Activating Token Index: 382

Text #19

Max Range: 3.5122. Min Range: -3.5122

Max Act: 3.3955. Min Act: -0.1700

Data Index: 2899668 (Open Web Text)

Max Activating Token Index: 512