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

Dataset: Open Web Text

Neuron 2816 in Layer 5

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: 3.1087. Min Range: -3.1087

Max Act: 3.1087. Min Act: -0.1700

Data Index: 8691717 (Open Web Text)

Max Activating Token Index: 613

Text #1

Max Range: 3.1087. Min Range: -3.1087

Max Act: 3.0957. Min Act: -0.1700

Data Index: 1586386 (Open Web Text)

Max Activating Token Index: 688

Text #2

Max Range: 3.1087. Min Range: -3.1087

Max Act: 3.0287. Min Act: -0.1700

Data Index: 6470006 (Open Web Text)

Max Activating Token Index: 180

Text #3

Max Range: 3.1087. Min Range: -3.1087

Max Act: 3.0297. Min Act: -0.1700

Data Index: 863045 (Open Web Text)

Max Activating Token Index: 437

Text #4

Max Range: 3.1087. Min Range: -3.1087

Max Act: 3.0010. Min Act: -0.1700

Data Index: 1925623 (Open Web Text)

Max Activating Token Index: 491

Text #5

Max Range: 3.1087. Min Range: -3.1087

Max Act: 3.0160. Min Act: -0.1700

Data Index: 4911438 (Open Web Text)

Max Activating Token Index: 128

Text #6

Max Range: 3.1087. Min Range: -3.1087

Max Act: 2.9856. Min Act: -0.1700

Data Index: 5004574 (Open Web Text)

Max Activating Token Index: 919

Text #7

Max Range: 3.1087. Min Range: -3.1087

Max Act: 3.0016. Min Act: -0.1700

Data Index: 2394490 (Open Web Text)

Max Activating Token Index: 26

Text #8

Max Range: 3.1087. Min Range: -3.1087

Max Act: 2.9774. Min Act: -0.1700

Data Index: 3483630 (Open Web Text)

Max Activating Token Index: 899

Text #9

Max Range: 3.1087. Min Range: -3.1087

Max Act: 2.9763. Min Act: -0.1700

Data Index: 6262093 (Open Web Text)

Max Activating Token Index: 845

Text #10

Max Range: 3.1087. Min Range: -3.1087

Max Act: 2.9788. Min Act: -0.1700

Data Index: 1878659 (Open Web Text)

Max Activating Token Index: 348

Text #11

Max Range: 3.1087. Min Range: -3.1087

Max Act: 2.9956. Min Act: -0.1700

Data Index: 6110124 (Open Web Text)

Max Activating Token Index: 407

Text #12

Max Range: 3.1087. Min Range: -3.1087

Max Act: 2.9771. Min Act: -0.1700

Data Index: 4421102 (Open Web Text)

Max Activating Token Index: 595

Text #13

Max Range: 3.1087. Min Range: -3.1087

Max Act: 2.9800. Min Act: -0.1700

Data Index: 1224346 (Open Web Text)

Max Activating Token Index: 941

Text #14

Max Range: 3.1087. Min Range: -3.1087

Max Act: 2.9750. Min Act: -0.1700

Data Index: 5090000 (Open Web Text)

Max Activating Token Index: 329

Text #15

Max Range: 3.1087. Min Range: -3.1087

Max Act: 2.9793. Min Act: -0.1700

Data Index: 4245017 (Open Web Text)

Max Activating Token Index: 308

Text #16

Max Range: 3.1087. Min Range: -3.1087

Max Act: 2.9738. Min Act: -0.1700

Data Index: 2022142 (Open Web Text)

Max Activating Token Index: 559

Text #17

Max Range: 3.1087. Min Range: -3.1087

Max Act: 2.9454. Min Act: -0.1700

Data Index: 616371 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 3.1087. Min Range: -3.1087

Max Act: 2.9505. Min Act: -0.1700

Data Index: 1313428 (Open Web Text)

Max Activating Token Index: 341

Text #19

Max Range: 3.1087. Min Range: -3.1087

Max Act: 2.9344. Min Act: -0.1700

Data Index: 636254 (Open Web Text)

Max Activating Token Index: 354