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

Dataset: Open Web Text

Neuron 968 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: 4.1150. Min Range: -4.1150

Max Act: 4.1150. Min Act: -0.1700

Data Index: 8717374 (Open Web Text)

Max Activating Token Index: 580

Text #1

Max Range: 4.1150. Min Range: -4.1150

Max Act: 3.9481. Min Act: -0.1700

Data Index: 4933428 (Open Web Text)

Max Activating Token Index: 126

Text #2

Max Range: 4.1150. Min Range: -4.1150

Max Act: 3.8209. Min Act: -0.1700

Data Index: 3772777 (Open Web Text)

Max Activating Token Index: 350

Text #3

Max Range: 4.1150. Min Range: -4.1150

Max Act: 3.7709. Min Act: -0.1700

Data Index: 5536568 (Open Web Text)

Max Activating Token Index: 369

Text #4

Max Range: 4.1150. Min Range: -4.1150

Max Act: 3.7739. Min Act: -0.1700

Data Index: 1411533 (Open Web Text)

Max Activating Token Index: 79

Text #5

Max Range: 4.1150. Min Range: -4.1150

Max Act: 3.7619. Min Act: -0.1700

Data Index: 7761081 (Open Web Text)

Max Activating Token Index: 564

Text #6

Max Range: 4.1150. Min Range: -4.1150

Max Act: 3.7556. Min Act: -0.1700

Data Index: 7717577 (Open Web Text)

Max Activating Token Index: 539

Text #7

Max Range: 4.1150. Min Range: -4.1150

Max Act: 3.7653. Min Act: -0.1700

Data Index: 1904053 (Open Web Text)

Max Activating Token Index: 284

Text #8

Max Range: 4.1150. Min Range: -4.1150

Max Act: 3.7434. Min Act: -0.1700

Data Index: 8465695 (Open Web Text)

Max Activating Token Index: 539

Text #9

Max Range: 4.1150. Min Range: -4.1150

Max Act: 3.7275. Min Act: -0.1700

Data Index: 6289975 (Open Web Text)

Max Activating Token Index: 56

Text #10

Max Range: 4.1150. Min Range: -4.1150

Max Act: 3.6792. Min Act: -0.1700

Data Index: 6206000 (Open Web Text)

Max Activating Token Index: 552

Text #11

Max Range: 4.1150. Min Range: -4.1150

Max Act: 3.6478. Min Act: -0.1700

Data Index: 4733750 (Open Web Text)

Max Activating Token Index: 1003

Text #12

Max Range: 4.1150. Min Range: -4.1150

Max Act: 3.6635. Min Act: -0.1700

Data Index: 1124849 (Open Web Text)

Max Activating Token Index: 507

Text #13

Max Range: 4.1150. Min Range: -4.1150

Max Act: 3.6470. Min Act: -0.1700

Data Index: 3429907 (Open Web Text)

Max Activating Token Index: 227

Text #14

Max Range: 4.1150. Min Range: -4.1150

Max Act: 3.6114. Min Act: -0.1700

Data Index: 1557459 (Open Web Text)

Max Activating Token Index: 99

Text #15

Max Range: 4.1150. Min Range: -4.1150

Max Act: 3.6427. Min Act: -0.1700

Data Index: 6588534 (Open Web Text)

Max Activating Token Index: 545

Text #16

Max Range: 4.1150. Min Range: -4.1150

Max Act: 3.6166. Min Act: -0.1700

Data Index: 7785089 (Open Web Text)

Max Activating Token Index: 333

Text #17

Max Range: 4.1150. Min Range: -4.1150

Max Act: 3.5972. Min Act: -0.1700

Data Index: 8427110 (Open Web Text)

Max Activating Token Index: 1012

Text #18

Max Range: 4.1150. Min Range: -4.1150

Max Act: 3.6153. Min Act: -0.1700

Data Index: 5899860 (Open Web Text)

Max Activating Token Index: 448

Text #19

Max Range: 4.1150. Min Range: -4.1150

Max Act: 3.6026. Min Act: -0.1700

Data Index: 7008160 (Open Web Text)

Max Activating Token Index: 60