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

Dataset: Open Web Text

Neuron 744 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: 3.3316. Min Range: -3.3316

Max Act: 3.3316. Min Act: -0.1700

Data Index: 6333589 (Open Web Text)

Max Activating Token Index: 649

Text #1

Max Range: 3.3316. Min Range: -3.3316

Max Act: 3.1657. Min Act: -0.1700

Data Index: 8148421 (Open Web Text)

Max Activating Token Index: 248

Text #2

Max Range: 3.3316. Min Range: -3.3316

Max Act: 3.1819. Min Act: -0.1700

Data Index: 4998622 (Open Web Text)

Max Activating Token Index: 556

Text #3

Max Range: 3.3316. Min Range: -3.3316

Max Act: 3.1834. Min Act: -0.1700

Data Index: 7495843 (Open Web Text)

Max Activating Token Index: 987

Text #4

Max Range: 3.3316. Min Range: -3.3316

Max Act: 3.1283. Min Act: -0.1700

Data Index: 944929 (Open Web Text)

Max Activating Token Index: 582

Text #5

Max Range: 3.3316. Min Range: -3.3316

Max Act: 3.0886. Min Act: -0.1700

Data Index: 1675204 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 3.3316. Min Range: -3.3316

Max Act: 3.0886. Min Act: -0.1700

Data Index: 5594826 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 3.3316. Min Range: -3.3316

Max Act: 3.0886. Min Act: -0.1700

Data Index: 3147875 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 3.3316. Min Range: -3.3316

Max Act: 3.0809. Min Act: -0.1700

Data Index: 1468902 (Open Web Text)

Max Activating Token Index: 33

Text #9

Max Range: 3.3316. Min Range: -3.3316

Max Act: 3.0752. Min Act: -0.1700

Data Index: 7769178 (Open Web Text)

Max Activating Token Index: 335

Text #10

Max Range: 3.3316. Min Range: -3.3316

Max Act: 3.0457. Min Act: -0.1700

Data Index: 5310750 (Open Web Text)

Max Activating Token Index: 960

Text #11

Max Range: 3.3316. Min Range: -3.3316

Max Act: 3.0837. Min Act: -0.1700

Data Index: 7481056 (Open Web Text)

Max Activating Token Index: 796

Text #12

Max Range: 3.3316. Min Range: -3.3316

Max Act: 3.0469. Min Act: -0.1700

Data Index: 2083509 (Open Web Text)

Max Activating Token Index: 103

Text #13

Max Range: 3.3316. Min Range: -3.3316

Max Act: 3.0675. Min Act: -0.1700

Data Index: 4671745 (Open Web Text)

Max Activating Token Index: 993

Text #14

Max Range: 3.3316. Min Range: -3.3316

Max Act: 3.0395. Min Act: -0.1700

Data Index: 8668524 (Open Web Text)

Max Activating Token Index: 137

Text #15

Max Range: 3.3316. Min Range: -3.3316

Max Act: 3.0215. Min Act: -0.1700

Data Index: 2417185 (Open Web Text)

Max Activating Token Index: 297

Text #16

Max Range: 3.3316. Min Range: -3.3316

Max Act: 2.9897. Min Act: -0.1700

Data Index: 5858587 (Open Web Text)

Max Activating Token Index: 1018

Text #17

Max Range: 3.3316. Min Range: -3.3316

Max Act: 2.9964. Min Act: -0.1700

Data Index: 1957695 (Open Web Text)

Max Activating Token Index: 278

Text #18

Max Range: 3.3316. Min Range: -3.3316

Max Act: 3.0292. Min Act: -0.1700

Data Index: 5974044 (Open Web Text)

Max Activating Token Index: 717

Text #19

Max Range: 3.3316. Min Range: -3.3316

Max Act: 2.9502. Min Act: -0.1700

Data Index: 6567782 (Open Web Text)

Max Activating Token Index: 840