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

Dataset: Open Web Text

Neuron 1765 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: 3.3741. Min Range: -3.3741

Max Act: 3.3685. Min Act: -0.1700

Data Index: 49438 (Open Web Text)

Max Activating Token Index: 1002

Text #1

Max Range: 3.3741. Min Range: -3.3741

Max Act: 3.3404. Min Act: -0.1700

Data Index: 5664390 (Open Web Text)

Max Activating Token Index: 874

Text #2

Max Range: 3.3741. Min Range: -3.3741

Max Act: 3.3741. Min Act: -0.1700

Data Index: 2730941 (Open Web Text)

Max Activating Token Index: 587

Text #3

Max Range: 3.3741. Min Range: -3.3741

Max Act: 3.3213. Min Act: -0.1700

Data Index: 733756 (Open Web Text)

Max Activating Token Index: 138

Text #4

Max Range: 3.3741. Min Range: -3.3741

Max Act: 3.3490. Min Act: -0.1700

Data Index: 7991741 (Open Web Text)

Max Activating Token Index: 461

Text #5

Max Range: 3.3741. Min Range: -3.3741

Max Act: 3.2825. Min Act: -0.1700

Data Index: 1386327 (Open Web Text)

Max Activating Token Index: 276

Text #6

Max Range: 3.3741. Min Range: -3.3741

Max Act: 3.2839. Min Act: -0.1700

Data Index: 6072535 (Open Web Text)

Max Activating Token Index: 949

Text #7

Max Range: 3.3741. Min Range: -3.3741

Max Act: 3.2625. Min Act: -0.1700

Data Index: 8068987 (Open Web Text)

Max Activating Token Index: 627

Text #8

Max Range: 3.3741. Min Range: -3.3741

Max Act: 3.2455. Min Act: -0.1700

Data Index: 5726913 (Open Web Text)

Max Activating Token Index: 334

Text #9

Max Range: 3.3741. Min Range: -3.3741

Max Act: 3.2466. Min Act: -0.1700

Data Index: 1931369 (Open Web Text)

Max Activating Token Index: 55

Text #10

Max Range: 3.3741. Min Range: -3.3741

Max Act: 3.2780. Min Act: -0.1700

Data Index: 6695674 (Open Web Text)

Max Activating Token Index: 932

Text #11

Max Range: 3.3741. Min Range: -3.3741

Max Act: 3.2310. Min Act: -0.1700

Data Index: 8786850 (Open Web Text)

Max Activating Token Index: 273

Text #12

Max Range: 3.3741. Min Range: -3.3741

Max Act: 3.2255. Min Act: -0.1700

Data Index: 8013870 (Open Web Text)

Max Activating Token Index: 988

Text #13

Max Range: 3.3741. Min Range: -3.3741

Max Act: 3.2439. Min Act: -0.1700

Data Index: 1000992 (Open Web Text)

Max Activating Token Index: 757

Text #14

Max Range: 3.3741. Min Range: -3.3741

Max Act: 3.2404. Min Act: -0.1700

Data Index: 5869405 (Open Web Text)

Max Activating Token Index: 931

Text #15

Max Range: 3.3741. Min Range: -3.3741

Max Act: 3.2350. Min Act: -0.1700

Data Index: 6978988 (Open Web Text)

Max Activating Token Index: 573

Text #16

Max Range: 3.3741. Min Range: -3.3741

Max Act: 3.2076. Min Act: -0.1700

Data Index: 896074 (Open Web Text)

Max Activating Token Index: 983

Text #17

Max Range: 3.3741. Min Range: -3.3741

Max Act: 3.1860. Min Act: -0.1700

Data Index: 8087820 (Open Web Text)

Max Activating Token Index: 702

Text #18

Max Range: 3.3741. Min Range: -3.3741

Max Act: 3.1942. Min Act: -0.1700

Data Index: 8410592 (Open Web Text)

Max Activating Token Index: 54

Text #19

Max Range: 3.3741. Min Range: -3.3741

Max Act: 3.1963. Min Act: -0.1700

Data Index: 8583353 (Open Web Text)

Max Activating Token Index: 312