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

Dataset: Open Web Text

Neuron 1788 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: 4.3414. Min Range: -4.3414

Max Act: 4.3414. Min Act: -0.1700

Data Index: 7517120 (Open Web Text)

Max Activating Token Index: 324

Text #1

Max Range: 4.3414. Min Range: -4.3414

Max Act: 4.1079. Min Act: -0.1700

Data Index: 6523515 (Open Web Text)

Max Activating Token Index: 573

Text #2

Max Range: 4.3414. Min Range: -4.3414

Max Act: 4.2005. Min Act: -0.1700

Data Index: 8739355 (Open Web Text)

Max Activating Token Index: 895

Text #3

Max Range: 4.3414. Min Range: -4.3414

Max Act: 4.1383. Min Act: -0.1700

Data Index: 313468 (Open Web Text)

Max Activating Token Index: 479

Text #4

Max Range: 4.3414. Min Range: -4.3414

Max Act: 4.1338. Min Act: -0.1700

Data Index: 4274226 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 4.3414. Min Range: -4.3414

Max Act: 4.1761. Min Act: -0.1700

Data Index: 2538586 (Open Web Text)

Max Activating Token Index: 720

Text #6

Max Range: 4.3414. Min Range: -4.3414

Max Act: 4.1177. Min Act: -0.1700

Data Index: 5232420 (Open Web Text)

Max Activating Token Index: 995

Text #7

Max Range: 4.3414. Min Range: -4.3414

Max Act: 4.0671. Min Act: -0.1700

Data Index: 7239732 (Open Web Text)

Max Activating Token Index: 550

Text #8

Max Range: 4.3414. Min Range: -4.3414

Max Act: 4.0701. Min Act: -0.1700

Data Index: 1954410 (Open Web Text)

Max Activating Token Index: 570

Text #9

Max Range: 4.3414. Min Range: -4.3414

Max Act: 4.0704. Min Act: -0.1700

Data Index: 3473693 (Open Web Text)

Max Activating Token Index: 514

Text #10

Max Range: 4.3414. Min Range: -4.3414

Max Act: 4.0807. Min Act: -0.1700

Data Index: 3902596 (Open Web Text)

Max Activating Token Index: 865

Text #11

Max Range: 4.3414. Min Range: -4.3414

Max Act: 4.0669. Min Act: -0.1700

Data Index: 7549342 (Open Web Text)

Max Activating Token Index: 107

Text #12

Max Range: 4.3414. Min Range: -4.3414

Max Act: 4.0481. Min Act: -0.1700

Data Index: 8402365 (Open Web Text)

Max Activating Token Index: 431

Text #13

Max Range: 4.3414. Min Range: -4.3414

Max Act: 4.0740. Min Act: -0.1700

Data Index: 2983692 (Open Web Text)

Max Activating Token Index: 546

Text #14

Max Range: 4.3414. Min Range: -4.3414

Max Act: 4.0342. Min Act: -0.1700

Data Index: 6421620 (Open Web Text)

Max Activating Token Index: 692

Text #15

Max Range: 4.3414. Min Range: -4.3414

Max Act: 4.0195. Min Act: -0.1700

Data Index: 436606 (Open Web Text)

Max Activating Token Index: 777

Text #16

Max Range: 4.3414. Min Range: -4.3414

Max Act: 4.0365. Min Act: -0.1700

Data Index: 8665843 (Open Web Text)

Max Activating Token Index: 542

Text #17

Max Range: 4.3414. Min Range: -4.3414

Max Act: 4.0632. Min Act: -0.1700

Data Index: 1913758 (Open Web Text)

Max Activating Token Index: 951

Text #18

Max Range: 4.3414. Min Range: -4.3414

Max Act: 4.0149. Min Act: -0.1700

Data Index: 1150690 (Open Web Text)

Max Activating Token Index: 625

Text #19

Max Range: 4.3414. Min Range: -4.3414

Max Act: 3.9894. Min Act: -0.1700

Data Index: 3217784 (Open Web Text)

Max Activating Token Index: 919