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

Dataset: Open Web Text

Neuron 124 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: 3.1812. Min Range: -3.1812

Max Act: 3.1790. Min Act: -0.1700

Data Index: 4319952 (Open Web Text)

Max Activating Token Index: 622

Text #1

Max Range: 3.1812. Min Range: -3.1812

Max Act: 3.1812. Min Act: -0.1700

Data Index: 985906 (Open Web Text)

Max Activating Token Index: 128

Text #2

Max Range: 3.1812. Min Range: -3.1812

Max Act: 3.1103. Min Act: -0.1700

Data Index: 2837494 (Open Web Text)

Max Activating Token Index: 695

Text #3

Max Range: 3.1812. Min Range: -3.1812

Max Act: 3.1191. Min Act: -0.1700

Data Index: 951564 (Open Web Text)

Max Activating Token Index: 938

Text #4

Max Range: 3.1812. Min Range: -3.1812

Max Act: 3.1392. Min Act: -0.1700

Data Index: 7163248 (Open Web Text)

Max Activating Token Index: 814

Text #5

Max Range: 3.1812. Min Range: -3.1812

Max Act: 3.0973. Min Act: -0.1700

Data Index: 5066106 (Open Web Text)

Max Activating Token Index: 273

Text #6

Max Range: 3.1812. Min Range: -3.1812

Max Act: 3.1048. Min Act: -0.1700

Data Index: 3573958 (Open Web Text)

Max Activating Token Index: 49

Text #7

Max Range: 3.1812. Min Range: -3.1812

Max Act: 3.0748. Min Act: -0.1700

Data Index: 2793042 (Open Web Text)

Max Activating Token Index: 32

Text #8

Max Range: 3.1812. Min Range: -3.1812

Max Act: 3.0613. Min Act: -0.1700

Data Index: 7498755 (Open Web Text)

Max Activating Token Index: 509

Text #9

Max Range: 3.1812. Min Range: -3.1812

Max Act: 3.0710. Min Act: -0.1700

Data Index: 196124 (Open Web Text)

Max Activating Token Index: 451

Text #10

Max Range: 3.1812. Min Range: -3.1812

Max Act: 3.0690. Min Act: -0.1700

Data Index: 3241596 (Open Web Text)

Max Activating Token Index: 428

Text #11

Max Range: 3.1812. Min Range: -3.1812

Max Act: 3.0549. Min Act: -0.1700

Data Index: 2548201 (Open Web Text)

Max Activating Token Index: 201

Text #12

Max Range: 3.1812. Min Range: -3.1812

Max Act: 3.0654. Min Act: -0.1700

Data Index: 495994 (Open Web Text)

Max Activating Token Index: 595

Text #13

Max Range: 3.1812. Min Range: -3.1812

Max Act: 3.0773. Min Act: -0.1700

Data Index: 8831050 (Open Web Text)

Max Activating Token Index: 615

Text #14

Max Range: 3.1812. Min Range: -3.1812

Max Act: 3.0461. Min Act: -0.1700

Data Index: 6290308 (Open Web Text)

Max Activating Token Index: 49

Text #15

Max Range: 3.1812. Min Range: -3.1812

Max Act: 3.0473. Min Act: -0.1700

Data Index: 6255929 (Open Web Text)

Max Activating Token Index: 97

Text #16

Max Range: 3.1812. Min Range: -3.1812

Max Act: 3.0593. Min Act: -0.1700

Data Index: 6253866 (Open Web Text)

Max Activating Token Index: 344

Text #17

Max Range: 3.1812. Min Range: -3.1812

Max Act: 3.0323. Min Act: -0.1700

Data Index: 8453198 (Open Web Text)

Max Activating Token Index: 971

Text #18

Max Range: 3.1812. Min Range: -3.1812

Max Act: 3.0346. Min Act: -0.1700

Data Index: 3089990 (Open Web Text)

Max Activating Token Index: 659

Text #19

Max Range: 3.1812. Min Range: -3.1812

Max Act: 3.0334. Min Act: -0.1700

Data Index: 4343299 (Open Web Text)

Max Activating Token Index: 818