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

Dataset: Open Web Text

Neuron 81 in Layer 1

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: 1.6056. Min Range: -1.6056

Max Act: 1.6056. Min Act: -0.1700

Data Index: 8315101 (Open Web Text)

Max Activating Token Index: 539

Text #1

Max Range: 1.6056. Min Range: -1.6056

Max Act: 1.2219. Min Act: -0.1700

Data Index: 4799920 (Open Web Text)

Max Activating Token Index: 526

Text #2

Max Range: 1.6056. Min Range: -1.6056

Max Act: 1.1975. Min Act: -0.1700

Data Index: 5028479 (Open Web Text)

Max Activating Token Index: 503

Text #3

Max Range: 1.6056. Min Range: -1.6056

Max Act: 1.2219. Min Act: -0.1700

Data Index: 3668008 (Open Web Text)

Max Activating Token Index: 519

Text #4

Max Range: 1.6056. Min Range: -1.6056

Max Act: 1.1484. Min Act: -0.1700

Data Index: 702209 (Open Web Text)

Max Activating Token Index: 598

Text #5

Max Range: 1.6056. Min Range: -1.6056

Max Act: 1.1439. Min Act: -0.1700

Data Index: 401356 (Open Web Text)

Max Activating Token Index: 581

Text #6

Max Range: 1.6056. Min Range: -1.6056

Max Act: 1.1447. Min Act: -0.1700

Data Index: 4750374 (Open Web Text)

Max Activating Token Index: 586

Text #7

Max Range: 1.6056. Min Range: -1.6056

Max Act: 1.1399. Min Act: -0.1700

Data Index: 5200986 (Open Web Text)

Max Activating Token Index: 527

Text #8

Max Range: 1.6056. Min Range: -1.6056

Max Act: 1.1270. Min Act: -0.1700

Data Index: 1790482 (Open Web Text)

Max Activating Token Index: 541

Text #9

Max Range: 1.6056. Min Range: -1.6056

Max Act: 1.1308. Min Act: -0.1700

Data Index: 2049725 (Open Web Text)

Max Activating Token Index: 547

Text #10

Max Range: 1.6056. Min Range: -1.6056

Max Act: 1.0882. Min Act: -0.1700

Data Index: 1610857 (Open Web Text)

Max Activating Token Index: 577

Text #11

Max Range: 1.6056. Min Range: -1.6056

Max Act: 1.1046. Min Act: -0.1700

Data Index: 1790473 (Open Web Text)

Max Activating Token Index: 547

Text #12

Max Range: 1.6056. Min Range: -1.6056

Max Act: 1.0905. Min Act: -0.1700

Data Index: 4750376 (Open Web Text)

Max Activating Token Index: 548

Text #13

Max Range: 1.6056. Min Range: -1.6056

Max Act: 1.1077. Min Act: -0.1700

Data Index: 5028481 (Open Web Text)

Max Activating Token Index: 532

Text #14

Max Range: 1.6056. Min Range: -1.6056

Max Act: 1.0989. Min Act: -0.1700

Data Index: 2482454 (Open Web Text)

Max Activating Token Index: 583

Text #15

Max Range: 1.6056. Min Range: -1.6056

Max Act: 1.0924. Min Act: -0.1700

Data Index: 7641771 (Open Web Text)

Max Activating Token Index: 570

Text #16

Max Range: 1.6056. Min Range: -1.6056

Max Act: 1.0770. Min Act: -0.1700

Data Index: 6728036 (Open Web Text)

Max Activating Token Index: 603

Text #17

Max Range: 1.6056. Min Range: -1.6056

Max Act: 1.0840. Min Act: -0.1700

Data Index: 4054483 (Open Web Text)

Max Activating Token Index: 561

Text #18

Max Range: 1.6056. Min Range: -1.6056

Max Act: 1.0518. Min Act: -0.1700

Data Index: 8640381 (Open Web Text)

Max Activating Token Index: 524

Text #19

Max Range: 1.6056. Min Range: -1.6056

Max Act: 1.0547. Min Act: -0.1700

Data Index: 776376 (Open Web Text)

Max Activating Token Index: 576