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

Dataset: Open Web Text

Neuron 1746 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: 5.3398. Min Range: -5.3398

Max Act: 5.3398. Min Act: -0.1700

Data Index: 5956669 (Open Web Text)

Max Activating Token Index: 715

Text #1

Max Range: 5.3398. Min Range: -5.3398

Max Act: 5.2795. Min Act: -0.1700

Data Index: 1248207 (Open Web Text)

Max Activating Token Index: 416

Text #2

Max Range: 5.3398. Min Range: -5.3398

Max Act: 5.2232. Min Act: -0.1700

Data Index: 2901891 (Open Web Text)

Max Activating Token Index: 993

Text #3

Max Range: 5.3398. Min Range: -5.3398

Max Act: 5.1903. Min Act: -0.1700

Data Index: 3777842 (Open Web Text)

Max Activating Token Index: 893

Text #4

Max Range: 5.3398. Min Range: -5.3398

Max Act: 5.2076. Min Act: -0.1700

Data Index: 1772549 (Open Web Text)

Max Activating Token Index: 960

Text #5

Max Range: 5.3398. Min Range: -5.3398

Max Act: 5.1491. Min Act: -0.1700

Data Index: 3802901 (Open Web Text)

Max Activating Token Index: 56

Text #6

Max Range: 5.3398. Min Range: -5.3398

Max Act: 5.1563. Min Act: -0.1700

Data Index: 6263278 (Open Web Text)

Max Activating Token Index: 412

Text #7

Max Range: 5.3398. Min Range: -5.3398

Max Act: 5.1750. Min Act: -0.1700

Data Index: 2531934 (Open Web Text)

Max Activating Token Index: 431

Text #8

Max Range: 5.3398. Min Range: -5.3398

Max Act: 5.1279. Min Act: -0.1700

Data Index: 3229255 (Open Web Text)

Max Activating Token Index: 618

Text #9

Max Range: 5.3398. Min Range: -5.3398

Max Act: 5.1277. Min Act: -0.1700

Data Index: 1248206 (Open Web Text)

Max Activating Token Index: 924

Text #10

Max Range: 5.3398. Min Range: -5.3398

Max Act: 5.1595. Min Act: -0.1700

Data Index: 261378 (Open Web Text)

Max Activating Token Index: 694

Text #11

Max Range: 5.3398. Min Range: -5.3398

Max Act: 5.1570. Min Act: -0.1700

Data Index: 5625014 (Open Web Text)

Max Activating Token Index: 331

Text #12

Max Range: 5.3398. Min Range: -5.3398

Max Act: 5.1404. Min Act: -0.1700

Data Index: 625956 (Open Web Text)

Max Activating Token Index: 920

Text #13

Max Range: 5.3398. Min Range: -5.3398

Max Act: 5.1424. Min Act: -0.1700

Data Index: 2967698 (Open Web Text)

Max Activating Token Index: 514

Text #14

Max Range: 5.3398. Min Range: -5.3398

Max Act: 5.1347. Min Act: -0.1700

Data Index: 717079 (Open Web Text)

Max Activating Token Index: 139

Text #15

Max Range: 5.3398. Min Range: -5.3398

Max Act: 5.1453. Min Act: -0.1700

Data Index: 1308864 (Open Web Text)

Max Activating Token Index: 385

Text #16

Max Range: 5.3398. Min Range: -5.3398

Max Act: 5.1080. Min Act: -0.1700

Data Index: 3909504 (Open Web Text)

Max Activating Token Index: 986

Text #17

Max Range: 5.3398. Min Range: -5.3398

Max Act: 5.1141. Min Act: -0.1700

Data Index: 3524313 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 5.3398. Min Range: -5.3398

Max Act: 5.0973. Min Act: -0.1700

Data Index: 1260976 (Open Web Text)

Max Activating Token Index: 260

Text #19

Max Range: 5.3398. Min Range: -5.3398

Max Act: 5.1009. Min Act: -0.1700

Data Index: 2601661 (Open Web Text)

Max Activating Token Index: 125