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

Dataset: Open Web Text

Neuron 1883 in Layer 2

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: 1.9582. Min Range: -1.9582

Max Act: 1.9582. Min Act: -0.1699

Data Index: 2792612 (Open Web Text)

Max Activating Token Index: 163

Text #1

Max Range: 1.9582. Min Range: -1.9582

Max Act: 1.8765. Min Act: -0.1699

Data Index: 4497116 (Open Web Text)

Max Activating Token Index: 215

Text #2

Max Range: 1.9582. Min Range: -1.9582

Max Act: 1.8705. Min Act: -0.1700

Data Index: 8089090 (Open Web Text)

Max Activating Token Index: 109

Text #3

Max Range: 1.9582. Min Range: -1.9582

Max Act: 1.8598. Min Act: -0.1700

Data Index: 7840960 (Open Web Text)

Max Activating Token Index: 145

Text #4

Max Range: 1.9582. Min Range: -1.9582

Max Act: 1.8312. Min Act: -0.1700

Data Index: 3013934 (Open Web Text)

Max Activating Token Index: 499

Text #5

Max Range: 1.9582. Min Range: -1.9582

Max Act: 1.8026. Min Act: -0.1700

Data Index: 4367986 (Open Web Text)

Max Activating Token Index: 177

Text #6

Max Range: 1.9582. Min Range: -1.9582

Max Act: 1.8036. Min Act: -0.1700

Data Index: 2786190 (Open Web Text)

Max Activating Token Index: 517

Text #7

Max Range: 1.9582. Min Range: -1.9582

Max Act: 1.8044. Min Act: -0.1700

Data Index: 7786496 (Open Web Text)

Max Activating Token Index: 446

Text #8

Max Range: 1.9582. Min Range: -1.9582

Max Act: 1.8108. Min Act: -0.1700

Data Index: 3059273 (Open Web Text)

Max Activating Token Index: 1022

Text #9

Max Range: 1.9582. Min Range: -1.9582

Max Act: 1.7973. Min Act: -0.1700

Data Index: 6819952 (Open Web Text)

Max Activating Token Index: 814

Text #10

Max Range: 1.9582. Min Range: -1.9582

Max Act: 1.7808. Min Act: -0.1700

Data Index: 4465429 (Open Web Text)

Max Activating Token Index: 606

Text #11

Max Range: 1.9582. Min Range: -1.9582

Max Act: 1.7812. Min Act: -0.1700

Data Index: 3942969 (Open Web Text)

Max Activating Token Index: 568

Text #12

Max Range: 1.9582. Min Range: -1.9582

Max Act: 1.8000. Min Act: -0.1700

Data Index: 6819953 (Open Web Text)

Max Activating Token Index: 570

Text #13

Max Range: 1.9582. Min Range: -1.9582

Max Act: 1.7884. Min Act: -0.1700

Data Index: 4684778 (Open Web Text)

Max Activating Token Index: 366

Text #14

Max Range: 1.9582. Min Range: -1.9582

Max Act: 1.7822. Min Act: -0.1700

Data Index: 4718457 (Open Web Text)

Max Activating Token Index: 411

Text #15

Max Range: 1.9582. Min Range: -1.9582

Max Act: 1.7853. Min Act: -0.1700

Data Index: 1339630 (Open Web Text)

Max Activating Token Index: 221

Text #16

Max Range: 1.9582. Min Range: -1.9582

Max Act: 1.7780. Min Act: -0.1700

Data Index: 1777899 (Open Web Text)

Max Activating Token Index: 957

Text #17

Max Range: 1.9582. Min Range: -1.9582

Max Act: 1.7851. Min Act: -0.1700

Data Index: 7806925 (Open Web Text)

Max Activating Token Index: 857

Text #18

Max Range: 1.9582. Min Range: -1.9582

Max Act: 1.7732. Min Act: -0.1700

Data Index: 7909158 (Open Web Text)

Max Activating Token Index: 55

Text #19

Max Range: 1.9582. Min Range: -1.9582

Max Act: 1.7841. Min Act: -0.1700

Data Index: 515626 (Open Web Text)

Max Activating Token Index: 564