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

Dataset: Open Web Text

Neuron 2754 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: 4.1844. Min Range: -4.1844

Max Act: 4.1844. Min Act: -0.1700

Data Index: 3094732 (Open Web Text)

Max Activating Token Index: 1004

Text #1

Max Range: 4.1844. Min Range: -4.1844

Max Act: 4.1122. Min Act: -0.1700

Data Index: 4269127 (Open Web Text)

Max Activating Token Index: 916

Text #2

Max Range: 4.1844. Min Range: -4.1844

Max Act: 4.0549. Min Act: -0.1700

Data Index: 2339864 (Open Web Text)

Max Activating Token Index: 602

Text #3

Max Range: 4.1844. Min Range: -4.1844

Max Act: 3.9985. Min Act: -0.1700

Data Index: 5110777 (Open Web Text)

Max Activating Token Index: 558

Text #4

Max Range: 4.1844. Min Range: -4.1844

Max Act: 3.9571. Min Act: -0.1700

Data Index: 8064930 (Open Web Text)

Max Activating Token Index: 568

Text #5

Max Range: 4.1844. Min Range: -4.1844

Max Act: 3.9533. Min Act: -0.1700

Data Index: 4595062 (Open Web Text)

Max Activating Token Index: 758

Text #6

Max Range: 4.1844. Min Range: -4.1844

Max Act: 3.8956. Min Act: -0.1700

Data Index: 8494542 (Open Web Text)

Max Activating Token Index: 537

Text #7

Max Range: 4.1844. Min Range: -4.1844

Max Act: 3.8455. Min Act: -0.1700

Data Index: 7903205 (Open Web Text)

Max Activating Token Index: 527

Text #8

Max Range: 4.1844. Min Range: -4.1844

Max Act: 3.8823. Min Act: -0.1700

Data Index: 4539369 (Open Web Text)

Max Activating Token Index: 235

Text #9

Max Range: 4.1844. Min Range: -4.1844

Max Act: 3.8938. Min Act: -0.1700

Data Index: 169721 (Open Web Text)

Max Activating Token Index: 641

Text #10

Max Range: 4.1844. Min Range: -4.1844

Max Act: 3.8769. Min Act: -0.1700

Data Index: 8638366 (Open Web Text)

Max Activating Token Index: 856

Text #11

Max Range: 4.1844. Min Range: -4.1844

Max Act: 3.8603. Min Act: -0.1700

Data Index: 645577 (Open Web Text)

Max Activating Token Index: 421

Text #12

Max Range: 4.1844. Min Range: -4.1844

Max Act: 3.8602. Min Act: -0.1700

Data Index: 7445341 (Open Web Text)

Max Activating Token Index: 263

Text #13

Max Range: 4.1844. Min Range: -4.1844

Max Act: 3.8085. Min Act: -0.1700

Data Index: 1424807 (Open Web Text)

Max Activating Token Index: 423

Text #14

Max Range: 4.1844. Min Range: -4.1844

Max Act: 3.8097. Min Act: -0.1700

Data Index: 6502112 (Open Web Text)

Max Activating Token Index: 92

Text #15

Max Range: 4.1844. Min Range: -4.1844

Max Act: 3.8475. Min Act: -0.1700

Data Index: 6990305 (Open Web Text)

Max Activating Token Index: 531

Text #16

Max Range: 4.1844. Min Range: -4.1844

Max Act: 3.7928. Min Act: -0.1700

Data Index: 3577869 (Open Web Text)

Max Activating Token Index: 900

Text #17

Max Range: 4.1844. Min Range: -4.1844

Max Act: 3.7794. Min Act: -0.1700

Data Index: 7400512 (Open Web Text)

Max Activating Token Index: 228

Text #18

Max Range: 4.1844. Min Range: -4.1844

Max Act: 3.8001. Min Act: -0.1700

Data Index: 4469795 (Open Web Text)

Max Activating Token Index: 401

Text #19

Max Range: 4.1844. Min Range: -4.1844

Max Act: 3.7667. Min Act: -0.1700

Data Index: 6009292 (Open Web Text)

Max Activating Token Index: 416