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

Dataset: Open Web Text

Neuron 83 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: 4.0898. Min Range: -4.0898

Max Act: 4.0898. Min Act: -0.1700

Data Index: 1964406 (Open Web Text)

Max Activating Token Index: 554

Text #1

Max Range: 4.0898. Min Range: -4.0898

Max Act: 4.0220. Min Act: -0.1700

Data Index: 5012311 (Open Web Text)

Max Activating Token Index: 695

Text #2

Max Range: 4.0898. Min Range: -4.0898

Max Act: 3.9202. Min Act: -0.1700

Data Index: 1263215 (Open Web Text)

Max Activating Token Index: 856

Text #3

Max Range: 4.0898. Min Range: -4.0898

Max Act: 3.8973. Min Act: -0.1700

Data Index: 1348283 (Open Web Text)

Max Activating Token Index: 368

Text #4

Max Range: 4.0898. Min Range: -4.0898

Max Act: 3.9163. Min Act: -0.1700

Data Index: 583373 (Open Web Text)

Max Activating Token Index: 546

Text #5

Max Range: 4.0898. Min Range: -4.0898

Max Act: 3.8532. Min Act: -0.1700

Data Index: 2674277 (Open Web Text)

Max Activating Token Index: 533

Text #6

Max Range: 4.0898. Min Range: -4.0898

Max Act: 3.8371. Min Act: -0.1700

Data Index: 1058819 (Open Web Text)

Max Activating Token Index: 976

Text #7

Max Range: 4.0898. Min Range: -4.0898

Max Act: 3.8590. Min Act: -0.1700

Data Index: 1805289 (Open Web Text)

Max Activating Token Index: 110

Text #8

Max Range: 4.0898. Min Range: -4.0898

Max Act: 3.8404. Min Act: -0.1700

Data Index: 7020584 (Open Web Text)

Max Activating Token Index: 606

Text #9

Max Range: 4.0898. Min Range: -4.0898

Max Act: 3.8482. Min Act: -0.1700

Data Index: 5534039 (Open Web Text)

Max Activating Token Index: 126

Text #10

Max Range: 4.0898. Min Range: -4.0898

Max Act: 3.8118. Min Act: -0.1700

Data Index: 4919504 (Open Web Text)

Max Activating Token Index: 512

Text #11

Max Range: 4.0898. Min Range: -4.0898

Max Act: 3.7848. Min Act: -0.1700

Data Index: 72840 (Open Web Text)

Max Activating Token Index: 461

Text #12

Max Range: 4.0898. Min Range: -4.0898

Max Act: 3.8271. Min Act: -0.1700

Data Index: 5203482 (Open Web Text)

Max Activating Token Index: 678

Text #13

Max Range: 4.0898. Min Range: -4.0898

Max Act: 3.7955. Min Act: -0.1700

Data Index: 2384385 (Open Web Text)

Max Activating Token Index: 346

Text #14

Max Range: 4.0898. Min Range: -4.0898

Max Act: 3.8041. Min Act: -0.1700

Data Index: 5930232 (Open Web Text)

Max Activating Token Index: 894

Text #15

Max Range: 4.0898. Min Range: -4.0898

Max Act: 3.7995. Min Act: -0.1700

Data Index: 355065 (Open Web Text)

Max Activating Token Index: 903

Text #16

Max Range: 4.0898. Min Range: -4.0898

Max Act: 3.7600. Min Act: -0.1700

Data Index: 4100034 (Open Web Text)

Max Activating Token Index: 139

Text #17

Max Range: 4.0898. Min Range: -4.0898

Max Act: 3.7499. Min Act: -0.1700

Data Index: 3687970 (Open Web Text)

Max Activating Token Index: 451

Text #18

Max Range: 4.0898. Min Range: -4.0898

Max Act: 3.7359. Min Act: -0.1700

Data Index: 825479 (Open Web Text)

Max Activating Token Index: 444

Text #19

Max Range: 4.0898. Min Range: -4.0898

Max Act: 3.7902. Min Act: -0.1700

Data Index: 3809610 (Open Web Text)

Max Activating Token Index: 679