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

Dataset: Open Web Text

Neuron 883 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: 2.7744. Min Range: -2.7744

Max Act: 2.7744. Min Act: -0.1700

Data Index: 5295454 (Open Web Text)

Max Activating Token Index: 485

Text #1

Max Range: 2.7744. Min Range: -2.7744

Max Act: 2.7370. Min Act: -0.1700

Data Index: 902580 (Open Web Text)

Max Activating Token Index: 829

Text #2

Max Range: 2.7744. Min Range: -2.7744

Max Act: 2.6943. Min Act: -0.1700

Data Index: 1331377 (Open Web Text)

Max Activating Token Index: 927

Text #3

Max Range: 2.7744. Min Range: -2.7744

Max Act: 2.7464. Min Act: -0.1700

Data Index: 7160967 (Open Web Text)

Max Activating Token Index: 981

Text #4

Max Range: 2.7744. Min Range: -2.7744

Max Act: 2.7170. Min Act: -0.1700

Data Index: 397613 (Open Web Text)

Max Activating Token Index: 467

Text #5

Max Range: 2.7744. Min Range: -2.7744

Max Act: 2.7379. Min Act: -0.1700

Data Index: 8819389 (Open Web Text)

Max Activating Token Index: 835

Text #6

Max Range: 2.7744. Min Range: -2.7744

Max Act: 2.7013. Min Act: -0.1700

Data Index: 1591331 (Open Web Text)

Max Activating Token Index: 465

Text #7

Max Range: 2.7744. Min Range: -2.7744

Max Act: 2.7029. Min Act: -0.1700

Data Index: 2447673 (Open Web Text)

Max Activating Token Index: 591

Text #8

Max Range: 2.7744. Min Range: -2.7744

Max Act: 2.7172. Min Act: -0.1700

Data Index: 1816552 (Open Web Text)

Max Activating Token Index: 823

Text #9

Max Range: 2.7744. Min Range: -2.7744

Max Act: 2.7090. Min Act: -0.1700

Data Index: 4419106 (Open Web Text)

Max Activating Token Index: 724

Text #10

Max Range: 2.7744. Min Range: -2.7744

Max Act: 2.6916. Min Act: -0.1700

Data Index: 2583939 (Open Web Text)

Max Activating Token Index: 470

Text #11

Max Range: 2.7744. Min Range: -2.7744

Max Act: 2.7040. Min Act: -0.1700

Data Index: 6237542 (Open Web Text)

Max Activating Token Index: 446

Text #12

Max Range: 2.7744. Min Range: -2.7744

Max Act: 2.6700. Min Act: -0.1700

Data Index: 2517812 (Open Web Text)

Max Activating Token Index: 664

Text #13

Max Range: 2.7744. Min Range: -2.7744

Max Act: 2.6897. Min Act: -0.1700

Data Index: 4169548 (Open Web Text)

Max Activating Token Index: 442

Text #14

Max Range: 2.7744. Min Range: -2.7744

Max Act: 2.6632. Min Act: -0.1700

Data Index: 7443816 (Open Web Text)

Max Activating Token Index: 628

Text #15

Max Range: 2.7744. Min Range: -2.7744

Max Act: 2.6429. Min Act: -0.1700

Data Index: 3301864 (Open Web Text)

Max Activating Token Index: 915

Text #16

Max Range: 2.7744. Min Range: -2.7744

Max Act: 2.6564. Min Act: -0.1700

Data Index: 4537227 (Open Web Text)

Max Activating Token Index: 358

Text #17

Max Range: 2.7744. Min Range: -2.7744

Max Act: 2.6461. Min Act: -0.1700

Data Index: 2349257 (Open Web Text)

Max Activating Token Index: 188

Text #18

Max Range: 2.7744. Min Range: -2.7744

Max Act: 2.6452. Min Act: -0.1700

Data Index: 6254901 (Open Web Text)

Max Activating Token Index: 653

Text #19

Max Range: 2.7744. Min Range: -2.7744

Max Act: 2.6745. Min Act: -0.1700

Data Index: 6027103 (Open Web Text)

Max Activating Token Index: 855