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

Dataset: Open Web Text

Neuron 2051 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: 5.1540. Min Range: -5.1540

Max Act: 5.1540. Min Act: -0.1700

Data Index: 73481 (Open Web Text)

Max Activating Token Index: 344

Text #1

Max Range: 5.1540. Min Range: -5.1540

Max Act: 5.0625. Min Act: -0.1700

Data Index: 8311977 (Open Web Text)

Max Activating Token Index: 964

Text #2

Max Range: 5.1540. Min Range: -5.1540

Max Act: 5.0193. Min Act: -0.1700

Data Index: 5501725 (Open Web Text)

Max Activating Token Index: 444

Text #3

Max Range: 5.1540. Min Range: -5.1540

Max Act: 5.0167. Min Act: -0.1700

Data Index: 3558394 (Open Web Text)

Max Activating Token Index: 880

Text #4

Max Range: 5.1540. Min Range: -5.1540

Max Act: 4.9713. Min Act: -0.1700

Data Index: 752685 (Open Web Text)

Max Activating Token Index: 626

Text #5

Max Range: 5.1540. Min Range: -5.1540

Max Act: 4.9180. Min Act: -0.1700

Data Index: 55365 (Open Web Text)

Max Activating Token Index: 667

Text #6

Max Range: 5.1540. Min Range: -5.1540

Max Act: 4.9396. Min Act: -0.1700

Data Index: 3229425 (Open Web Text)

Max Activating Token Index: 989

Text #7

Max Range: 5.1540. Min Range: -5.1540

Max Act: 4.9737. Min Act: -0.1700

Data Index: 1331052 (Open Web Text)

Max Activating Token Index: 493

Text #8

Max Range: 5.1540. Min Range: -5.1540

Max Act: 4.9328. Min Act: -0.1700

Data Index: 2416069 (Open Web Text)

Max Activating Token Index: 252

Text #9

Max Range: 5.1540. Min Range: -5.1540

Max Act: 4.8916. Min Act: -0.1700

Data Index: 1402325 (Open Web Text)

Max Activating Token Index: 911

Text #10

Max Range: 5.1540. Min Range: -5.1540

Max Act: 4.8852. Min Act: -0.1700

Data Index: 6224241 (Open Web Text)

Max Activating Token Index: 537

Text #11

Max Range: 5.1540. Min Range: -5.1540

Max Act: 4.9060. Min Act: -0.1700

Data Index: 2389052 (Open Web Text)

Max Activating Token Index: 817

Text #12

Max Range: 5.1540. Min Range: -5.1540

Max Act: 4.9016. Min Act: -0.1700

Data Index: 3653566 (Open Web Text)

Max Activating Token Index: 810

Text #13

Max Range: 5.1540. Min Range: -5.1540

Max Act: 4.9158. Min Act: -0.1700

Data Index: 2241704 (Open Web Text)

Max Activating Token Index: 993

Text #14

Max Range: 5.1540. Min Range: -5.1540

Max Act: 4.9120. Min Act: -0.1700

Data Index: 2519257 (Open Web Text)

Max Activating Token Index: 754

Text #15

Max Range: 5.1540. Min Range: -5.1540

Max Act: 4.8868. Min Act: -0.1700

Data Index: 793959 (Open Web Text)

Max Activating Token Index: 473

Text #16

Max Range: 5.1540. Min Range: -5.1540

Max Act: 4.8580. Min Act: -0.1700

Data Index: 3201517 (Open Web Text)

Max Activating Token Index: 377

Text #17

Max Range: 5.1540. Min Range: -5.1540

Max Act: 4.8819. Min Act: -0.1700

Data Index: 3347695 (Open Web Text)

Max Activating Token Index: 239

Text #18

Max Range: 5.1540. Min Range: -5.1540

Max Act: 4.8982. Min Act: -0.1700

Data Index: 5164344 (Open Web Text)

Max Activating Token Index: 518

Text #19

Max Range: 5.1540. Min Range: -5.1540

Max Act: 4.8681. Min Act: -0.1700

Data Index: 1954970 (Open Web Text)

Max Activating Token Index: 344