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

Dataset: Open Web Text

Neuron 1022 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: 4.5732. Min Range: -4.5732

Max Act: 4.5732. Min Act: -0.1700

Data Index: 2484304 (Open Web Text)

Max Activating Token Index: 358

Text #1

Max Range: 4.5732. Min Range: -4.5732

Max Act: 4.5551. Min Act: -0.1700

Data Index: 8073258 (Open Web Text)

Max Activating Token Index: 689

Text #2

Max Range: 4.5732. Min Range: -4.5732

Max Act: 4.5282. Min Act: -0.1700

Data Index: 6389708 (Open Web Text)

Max Activating Token Index: 185

Text #3

Max Range: 4.5732. Min Range: -4.5732

Max Act: 4.5441. Min Act: -0.1700

Data Index: 6863109 (Open Web Text)

Max Activating Token Index: 301

Text #4

Max Range: 4.5732. Min Range: -4.5732

Max Act: 4.4811. Min Act: -0.1700

Data Index: 4727882 (Open Web Text)

Max Activating Token Index: 780

Text #5

Max Range: 4.5732. Min Range: -4.5732

Max Act: 4.4949. Min Act: -0.1700

Data Index: 4682910 (Open Web Text)

Max Activating Token Index: 45

Text #6

Max Range: 4.5732. Min Range: -4.5732

Max Act: 4.5209. Min Act: -0.1700

Data Index: 4361102 (Open Web Text)

Max Activating Token Index: 52

Text #7

Max Range: 4.5732. Min Range: -4.5732

Max Act: 4.4691. Min Act: -0.1700

Data Index: 7166228 (Open Web Text)

Max Activating Token Index: 214

Text #8

Max Range: 4.5732. Min Range: -4.5732

Max Act: 4.4792. Min Act: -0.1700

Data Index: 2615905 (Open Web Text)

Max Activating Token Index: 386

Text #9

Max Range: 4.5732. Min Range: -4.5732

Max Act: 4.4393. Min Act: -0.1700

Data Index: 7457943 (Open Web Text)

Max Activating Token Index: 153

Text #10

Max Range: 4.5732. Min Range: -4.5732

Max Act: 4.4771. Min Act: -0.1700

Data Index: 120243 (Open Web Text)

Max Activating Token Index: 608

Text #11

Max Range: 4.5732. Min Range: -4.5732

Max Act: 4.4312. Min Act: -0.1700

Data Index: 6899827 (Open Web Text)

Max Activating Token Index: 506

Text #12

Max Range: 4.5732. Min Range: -4.5732

Max Act: 4.4101. Min Act: -0.1700

Data Index: 8611810 (Open Web Text)

Max Activating Token Index: 493

Text #13

Max Range: 4.5732. Min Range: -4.5732

Max Act: 4.4743. Min Act: -0.1700

Data Index: 4279376 (Open Web Text)

Max Activating Token Index: 499

Text #14

Max Range: 4.5732. Min Range: -4.5732

Max Act: 4.4538. Min Act: -0.1700

Data Index: 619302 (Open Web Text)

Max Activating Token Index: 115

Text #15

Max Range: 4.5732. Min Range: -4.5732

Max Act: 4.4357. Min Act: -0.1700

Data Index: 8471810 (Open Web Text)

Max Activating Token Index: 562

Text #16

Max Range: 4.5732. Min Range: -4.5732

Max Act: 4.4310. Min Act: -0.1700

Data Index: 7466891 (Open Web Text)

Max Activating Token Index: 78

Text #17

Max Range: 4.5732. Min Range: -4.5732

Max Act: 4.4526. Min Act: -0.1700

Data Index: 825601 (Open Web Text)

Max Activating Token Index: 63

Text #18

Max Range: 4.5732. Min Range: -4.5732

Max Act: 4.3970. Min Act: -0.1700

Data Index: 1208930 (Open Web Text)

Max Activating Token Index: 52

Text #19

Max Range: 4.5732. Min Range: -4.5732

Max Act: 4.3717. Min Act: -0.1700

Data Index: 995750 (Open Web Text)

Max Activating Token Index: 499