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

Dataset: Open Web Text

Neuron 2648 in Layer 6

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: 4.4844. Min Range: -4.4844

Max Act: 4.4844. Min Act: -0.1700

Data Index: 8423577 (Open Web Text)

Max Activating Token Index: 458

Text #1

Max Range: 4.4844. Min Range: -4.4844

Max Act: 4.4553. Min Act: -0.1700

Data Index: 3966701 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 4.4844. Min Range: -4.4844

Max Act: 4.3657. Min Act: -0.1700

Data Index: 62544 (Open Web Text)

Max Activating Token Index: 477

Text #3

Max Range: 4.4844. Min Range: -4.4844

Max Act: 4.3411. Min Act: -0.1700

Data Index: 7689254 (Open Web Text)

Max Activating Token Index: 105

Text #4

Max Range: 4.4844. Min Range: -4.4844

Max Act: 4.3549. Min Act: -0.1700

Data Index: 6155721 (Open Web Text)

Max Activating Token Index: 842

Text #5

Max Range: 4.4844. Min Range: -4.4844

Max Act: 4.3317. Min Act: -0.1700

Data Index: 6387276 (Open Web Text)

Max Activating Token Index: 450

Text #6

Max Range: 4.4844. Min Range: -4.4844

Max Act: 4.3532. Min Act: -0.1700

Data Index: 7720876 (Open Web Text)

Max Activating Token Index: 16

Text #7

Max Range: 4.4844. Min Range: -4.4844

Max Act: 4.2917. Min Act: -0.1700

Data Index: 7593078 (Open Web Text)

Max Activating Token Index: 545

Text #8

Max Range: 4.4844. Min Range: -4.4844

Max Act: 4.2988. Min Act: -0.1700

Data Index: 640394 (Open Web Text)

Max Activating Token Index: 543

Text #9

Max Range: 4.4844. Min Range: -4.4844

Max Act: 4.2626. Min Act: -0.1700

Data Index: 743091 (Open Web Text)

Max Activating Token Index: 550

Text #10

Max Range: 4.4844. Min Range: -4.4844

Max Act: 4.2510. Min Act: -0.1700

Data Index: 6957312 (Open Web Text)

Max Activating Token Index: 800

Text #11

Max Range: 4.4844. Min Range: -4.4844

Max Act: 4.2365. Min Act: -0.1700

Data Index: 6182003 (Open Web Text)

Max Activating Token Index: 326

Text #12

Max Range: 4.4844. Min Range: -4.4844

Max Act: 4.2376. Min Act: -0.1700

Data Index: 5564300 (Open Web Text)

Max Activating Token Index: 528

Text #13

Max Range: 4.4844. Min Range: -4.4844

Max Act: 4.2344. Min Act: -0.1700

Data Index: 5514623 (Open Web Text)

Max Activating Token Index: 495

Text #14

Max Range: 4.4844. Min Range: -4.4844

Max Act: 4.2453. Min Act: -0.1700

Data Index: 3866595 (Open Web Text)

Max Activating Token Index: 387

Text #15

Max Range: 4.4844. Min Range: -4.4844

Max Act: 4.2272. Min Act: -0.1700

Data Index: 1875457 (Open Web Text)

Max Activating Token Index: 515

Text #16

Max Range: 4.4844. Min Range: -4.4844

Max Act: 4.2175. Min Act: -0.1700

Data Index: 8794615 (Open Web Text)

Max Activating Token Index: 434

Text #17

Max Range: 4.4844. Min Range: -4.4844

Max Act: 4.2133. Min Act: -0.1700

Data Index: 6930856 (Open Web Text)

Max Activating Token Index: 40

Text #18

Max Range: 4.4844. Min Range: -4.4844

Max Act: 4.1972. Min Act: -0.1700

Data Index: 4513524 (Open Web Text)

Max Activating Token Index: 565

Text #19

Max Range: 4.4844. Min Range: -4.4844

Max Act: 4.1753. Min Act: -0.1700

Data Index: 6620102 (Open Web Text)

Max Activating Token Index: 493