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

Dataset: Open Web Text

Neuron 548 in Layer 2

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: 3.6682. Min Range: -3.6682

Max Act: 3.6682. Min Act: -0.1700

Data Index: 8175879 (Open Web Text)

Max Activating Token Index: 725

Text #1

Max Range: 3.6682. Min Range: -3.6682

Max Act: 3.6305. Min Act: -0.1700

Data Index: 3399391 (Open Web Text)

Max Activating Token Index: 1010

Text #2

Max Range: 3.6682. Min Range: -3.6682

Max Act: 3.6157. Min Act: -0.1700

Data Index: 5796486 (Open Web Text)

Max Activating Token Index: 769

Text #3

Max Range: 3.6682. Min Range: -3.6682

Max Act: 3.5965. Min Act: -0.1700

Data Index: 8175880 (Open Web Text)

Max Activating Token Index: 329

Text #4

Max Range: 3.6682. Min Range: -3.6682

Max Act: 3.5690. Min Act: -0.1700

Data Index: 4695448 (Open Web Text)

Max Activating Token Index: 15

Text #5

Max Range: 3.6682. Min Range: -3.6682

Max Act: 3.5502. Min Act: -0.1700

Data Index: 3399392 (Open Web Text)

Max Activating Token Index: 85

Text #6

Max Range: 3.6682. Min Range: -3.6682

Max Act: 3.4928. Min Act: -0.1700

Data Index: 8299957 (Open Web Text)

Max Activating Token Index: 881

Text #7

Max Range: 3.6682. Min Range: -3.6682

Max Act: 3.4993. Min Act: -0.1700

Data Index: 8654828 (Open Web Text)

Max Activating Token Index: 570

Text #8

Max Range: 3.6682. Min Range: -3.6682

Max Act: 3.4577. Min Act: -0.1700

Data Index: 74638 (Open Web Text)

Max Activating Token Index: 666

Text #9

Max Range: 3.6682. Min Range: -3.6682

Max Act: 3.4627. Min Act: -0.1700

Data Index: 601473 (Open Web Text)

Max Activating Token Index: 246

Text #10

Max Range: 3.6682. Min Range: -3.6682

Max Act: 3.4808. Min Act: -0.1700

Data Index: 1796452 (Open Web Text)

Max Activating Token Index: 494

Text #11

Max Range: 3.6682. Min Range: -3.6682

Max Act: 3.4101. Min Act: -0.1700

Data Index: 449893 (Open Web Text)

Max Activating Token Index: 246

Text #12

Max Range: 3.6682. Min Range: -3.6682

Max Act: 3.3985. Min Act: -0.1700

Data Index: 7422338 (Open Web Text)

Max Activating Token Index: 114

Text #13

Max Range: 3.6682. Min Range: -3.6682

Max Act: 3.3911. Min Act: -0.1700

Data Index: 203914 (Open Web Text)

Max Activating Token Index: 623

Text #14

Max Range: 3.6682. Min Range: -3.6682

Max Act: 3.3774. Min Act: -0.1700

Data Index: 3011451 (Open Web Text)

Max Activating Token Index: 577

Text #15

Max Range: 3.6682. Min Range: -3.6682

Max Act: 3.3933. Min Act: -0.1700

Data Index: 7784925 (Open Web Text)

Max Activating Token Index: 902

Text #16

Max Range: 3.6682. Min Range: -3.6682

Max Act: 3.3941. Min Act: -0.1700

Data Index: 3463205 (Open Web Text)

Max Activating Token Index: 734

Text #17

Max Range: 3.6682. Min Range: -3.6682

Max Act: 3.3777. Min Act: -0.1700

Data Index: 6125653 (Open Web Text)

Max Activating Token Index: 773

Text #18

Max Range: 3.6682. Min Range: -3.6682

Max Act: 3.3691. Min Act: -0.1700

Data Index: 5796489 (Open Web Text)

Max Activating Token Index: 270

Text #19

Max Range: 3.6682. Min Range: -3.6682

Max Act: 3.3612. Min Act: -0.1700

Data Index: 143204 (Open Web Text)

Max Activating Token Index: 812