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

Dataset: Open Web Text

Neuron 1513 in Layer 4

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: 3.3152. Min Range: -3.3152

Max Act: 3.3152. Min Act: -0.1700

Data Index: 7450592 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 3.3152. Min Range: -3.3152

Max Act: 3.2909. Min Act: -0.1700

Data Index: 3811985 (Open Web Text)

Max Activating Token Index: 251

Text #2

Max Range: 3.3152. Min Range: -3.3152

Max Act: 3.2516. Min Act: -0.1700

Data Index: 2230260 (Open Web Text)

Max Activating Token Index: 91

Text #3

Max Range: 3.3152. Min Range: -3.3152

Max Act: 3.2458. Min Act: -0.1700

Data Index: 3849385 (Open Web Text)

Max Activating Token Index: 84

Text #4

Max Range: 3.3152. Min Range: -3.3152

Max Act: 3.2258. Min Act: -0.1700

Data Index: 5387553 (Open Web Text)

Max Activating Token Index: 409

Text #5

Max Range: 3.3152. Min Range: -3.3152

Max Act: 3.2424. Min Act: -0.1700

Data Index: 5297804 (Open Web Text)

Max Activating Token Index: 616

Text #6

Max Range: 3.3152. Min Range: -3.3152

Max Act: 3.2157. Min Act: -0.1700

Data Index: 4440837 (Open Web Text)

Max Activating Token Index: 597

Text #7

Max Range: 3.3152. Min Range: -3.3152

Max Act: 3.2172. Min Act: -0.1700

Data Index: 600110 (Open Web Text)

Max Activating Token Index: 981

Text #8

Max Range: 3.3152. Min Range: -3.3152

Max Act: 3.2023. Min Act: -0.1700

Data Index: 5714361 (Open Web Text)

Max Activating Token Index: 806

Text #9

Max Range: 3.3152. Min Range: -3.3152

Max Act: 3.2084. Min Act: -0.1700

Data Index: 1935226 (Open Web Text)

Max Activating Token Index: 657

Text #10

Max Range: 3.3152. Min Range: -3.3152

Max Act: 3.1985. Min Act: -0.1700

Data Index: 705818 (Open Web Text)

Max Activating Token Index: 882

Text #11

Max Range: 3.3152. Min Range: -3.3152

Max Act: 3.1895. Min Act: -0.1700

Data Index: 6157844 (Open Web Text)

Max Activating Token Index: 683

Text #12

Max Range: 3.3152. Min Range: -3.3152

Max Act: 3.1687. Min Act: -0.1700

Data Index: 5432656 (Open Web Text)

Max Activating Token Index: 731

Text #13

Max Range: 3.3152. Min Range: -3.3152

Max Act: 3.1798. Min Act: -0.1700

Data Index: 2196168 (Open Web Text)

Max Activating Token Index: 404

Text #14

Max Range: 3.3152. Min Range: -3.3152

Max Act: 3.1773. Min Act: -0.1700

Data Index: 2506555 (Open Web Text)

Max Activating Token Index: 58

Text #15

Max Range: 3.3152. Min Range: -3.3152

Max Act: 3.1794. Min Act: -0.1700

Data Index: 6280002 (Open Web Text)

Max Activating Token Index: 584

Text #16

Max Range: 3.3152. Min Range: -3.3152

Max Act: 3.1492. Min Act: -0.1700

Data Index: 7313024 (Open Web Text)

Max Activating Token Index: 387

Text #17

Max Range: 3.3152. Min Range: -3.3152

Max Act: 3.1696. Min Act: -0.1700

Data Index: 7638384 (Open Web Text)

Max Activating Token Index: 471

Text #18

Max Range: 3.3152. Min Range: -3.3152

Max Act: 3.1473. Min Act: -0.1700

Data Index: 1722438 (Open Web Text)

Max Activating Token Index: 585

Text #19

Max Range: 3.3152. Min Range: -3.3152

Max Act: 3.1646. Min Act: -0.1700

Data Index: 7894734 (Open Web Text)

Max Activating Token Index: 470