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

Dataset: Open Web Text

Neuron 2716 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: 3.3465. Min Range: -3.3465

Max Act: 3.3375. Min Act: -0.1700

Data Index: 6375988 (Open Web Text)

Max Activating Token Index: 772

Text #1

Max Range: 3.3465. Min Range: -3.3465

Max Act: 3.3035. Min Act: -0.1700

Data Index: 6247555 (Open Web Text)

Max Activating Token Index: 262

Text #2

Max Range: 3.3465. Min Range: -3.3465

Max Act: 3.3272. Min Act: -0.1700

Data Index: 3305846 (Open Web Text)

Max Activating Token Index: 848

Text #3

Max Range: 3.3465. Min Range: -3.3465

Max Act: 3.3465. Min Act: -0.1700

Data Index: 846831 (Open Web Text)

Max Activating Token Index: 435

Text #4

Max Range: 3.3465. Min Range: -3.3465

Max Act: 3.3186. Min Act: -0.1700

Data Index: 6236620 (Open Web Text)

Max Activating Token Index: 603

Text #5

Max Range: 3.3465. Min Range: -3.3465

Max Act: 3.3064. Min Act: -0.1700

Data Index: 8147611 (Open Web Text)

Max Activating Token Index: 781

Text #6

Max Range: 3.3465. Min Range: -3.3465

Max Act: 3.2720. Min Act: -0.1700

Data Index: 2803858 (Open Web Text)

Max Activating Token Index: 751

Text #7

Max Range: 3.3465. Min Range: -3.3465

Max Act: 3.2860. Min Act: -0.1700

Data Index: 5437203 (Open Web Text)

Max Activating Token Index: 581

Text #8

Max Range: 3.3465. Min Range: -3.3465

Max Act: 3.2910. Min Act: -0.1700

Data Index: 7005217 (Open Web Text)

Max Activating Token Index: 971

Text #9

Max Range: 3.3465. Min Range: -3.3465

Max Act: 3.2744. Min Act: -0.1700

Data Index: 4268980 (Open Web Text)

Max Activating Token Index: 919

Text #10

Max Range: 3.3465. Min Range: -3.3465

Max Act: 3.2865. Min Act: -0.1700

Data Index: 2829566 (Open Web Text)

Max Activating Token Index: 479

Text #11

Max Range: 3.3465. Min Range: -3.3465

Max Act: 3.3010. Min Act: -0.1700

Data Index: 7470340 (Open Web Text)

Max Activating Token Index: 476

Text #12

Max Range: 3.3465. Min Range: -3.3465

Max Act: 3.2960. Min Act: -0.1700

Data Index: 1126357 (Open Web Text)

Max Activating Token Index: 820

Text #13

Max Range: 3.3465. Min Range: -3.3465

Max Act: 3.2551. Min Act: -0.1700

Data Index: 417194 (Open Web Text)

Max Activating Token Index: 339

Text #14

Max Range: 3.3465. Min Range: -3.3465

Max Act: 3.2795. Min Act: -0.1700

Data Index: 5098736 (Open Web Text)

Max Activating Token Index: 940

Text #15

Max Range: 3.3465. Min Range: -3.3465

Max Act: 3.2781. Min Act: -0.1700

Data Index: 4392618 (Open Web Text)

Max Activating Token Index: 884

Text #16

Max Range: 3.3465. Min Range: -3.3465

Max Act: 3.2585. Min Act: -0.1700

Data Index: 6922353 (Open Web Text)

Max Activating Token Index: 205

Text #17

Max Range: 3.3465. Min Range: -3.3465

Max Act: 3.2410. Min Act: -0.1700

Data Index: 8582122 (Open Web Text)

Max Activating Token Index: 355

Text #18

Max Range: 3.3465. Min Range: -3.3465

Max Act: 3.2474. Min Act: -0.1700

Data Index: 6080494 (Open Web Text)

Max Activating Token Index: 679

Text #19

Max Range: 3.3465. Min Range: -3.3465

Max Act: 3.2102. Min Act: -0.1700

Data Index: 97222 (Open Web Text)

Max Activating Token Index: 650