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

Dataset: Open Web Text

Neuron 293 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: 6.5537. Min Range: -6.5537

Max Act: 6.5537. Min Act: -0.1700

Data Index: 6523739 (Open Web Text)

Max Activating Token Index: 779

Text #1

Max Range: 6.5537. Min Range: -6.5537

Max Act: 6.4893. Min Act: -0.1700

Data Index: 3870734 (Open Web Text)

Max Activating Token Index: 894

Text #2

Max Range: 6.5537. Min Range: -6.5537

Max Act: 6.3595. Min Act: -0.1700

Data Index: 5151336 (Open Web Text)

Max Activating Token Index: 715

Text #3

Max Range: 6.5537. Min Range: -6.5537

Max Act: 6.2978. Min Act: -0.1700

Data Index: 7943339 (Open Web Text)

Max Activating Token Index: 839

Text #4

Max Range: 6.5537. Min Range: -6.5537

Max Act: 6.3203. Min Act: -0.1700

Data Index: 6964521 (Open Web Text)

Max Activating Token Index: 809

Text #5

Max Range: 6.5537. Min Range: -6.5537

Max Act: 6.2996. Min Act: -0.1700

Data Index: 3870735 (Open Web Text)

Max Activating Token Index: 467

Text #6

Max Range: 6.5537. Min Range: -6.5537

Max Act: 6.2924. Min Act: -0.1700

Data Index: 5151322 (Open Web Text)

Max Activating Token Index: 976

Text #7

Max Range: 6.5537. Min Range: -6.5537

Max Act: 6.2157. Min Act: -0.1700

Data Index: 5001733 (Open Web Text)

Max Activating Token Index: 647

Text #8

Max Range: 6.5537. Min Range: -6.5537

Max Act: 6.2368. Min Act: -0.1700

Data Index: 3928362 (Open Web Text)

Max Activating Token Index: 473

Text #9

Max Range: 6.5537. Min Range: -6.5537

Max Act: 6.2500. Min Act: -0.1700

Data Index: 3928364 (Open Web Text)

Max Activating Token Index: 407

Text #10

Max Range: 6.5537. Min Range: -6.5537

Max Act: 6.2321. Min Act: -0.1700

Data Index: 6137427 (Open Web Text)

Max Activating Token Index: 871

Text #11

Max Range: 6.5537. Min Range: -6.5537

Max Act: 6.2364. Min Act: -0.1700

Data Index: 4159973 (Open Web Text)

Max Activating Token Index: 997

Text #12

Max Range: 6.5537. Min Range: -6.5537

Max Act: 6.1492. Min Act: -0.1700

Data Index: 6753604 (Open Web Text)

Max Activating Token Index: 756

Text #13

Max Range: 6.5537. Min Range: -6.5537

Max Act: 6.1799. Min Act: -0.1700

Data Index: 5151330 (Open Web Text)

Max Activating Token Index: 982

Text #14

Max Range: 6.5537. Min Range: -6.5537

Max Act: 6.1815. Min Act: -0.1700

Data Index: 5151338 (Open Web Text)

Max Activating Token Index: 960

Text #15

Max Range: 6.5537. Min Range: -6.5537

Max Act: 6.1958. Min Act: -0.1700

Data Index: 5151323 (Open Web Text)

Max Activating Token Index: 360

Text #16

Max Range: 6.5537. Min Range: -6.5537

Max Act: 6.1244. Min Act: -0.1700

Data Index: 8613555 (Open Web Text)

Max Activating Token Index: 616

Text #17

Max Range: 6.5537. Min Range: -6.5537

Max Act: 6.1261. Min Act: -0.1700

Data Index: 3045248 (Open Web Text)

Max Activating Token Index: 788

Text #18

Max Range: 6.5537. Min Range: -6.5537

Max Act: 6.1296. Min Act: -0.1700

Data Index: 5151337 (Open Web Text)

Max Activating Token Index: 1021

Text #19

Max Range: 6.5537. Min Range: -6.5537

Max Act: 6.0774. Min Act: -0.1700

Data Index: 1318504 (Open Web Text)

Max Activating Token Index: 1003