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

Dataset: Open Web Text

Neuron 1758 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: 4.5511. Min Range: -4.5511

Max Act: 4.5511. Min Act: -0.1700

Data Index: 3330346 (Open Web Text)

Max Activating Token Index: 645

Text #1

Max Range: 4.5511. Min Range: -4.5511

Max Act: 4.5123. Min Act: -0.1700

Data Index: 4910932 (Open Web Text)

Max Activating Token Index: 42

Text #2

Max Range: 4.5511. Min Range: -4.5511

Max Act: 4.5122. Min Act: -0.1700

Data Index: 6988665 (Open Web Text)

Max Activating Token Index: 439

Text #3

Max Range: 4.5511. Min Range: -4.5511

Max Act: 4.5077. Min Act: -0.1700

Data Index: 1484034 (Open Web Text)

Max Activating Token Index: 973

Text #4

Max Range: 4.5511. Min Range: -4.5511

Max Act: 4.4998. Min Act: -0.1700

Data Index: 1741069 (Open Web Text)

Max Activating Token Index: 567

Text #5

Max Range: 4.5511. Min Range: -4.5511

Max Act: 4.4767. Min Act: -0.1700

Data Index: 5120868 (Open Web Text)

Max Activating Token Index: 115

Text #6

Max Range: 4.5511. Min Range: -4.5511

Max Act: 4.4801. Min Act: -0.1700

Data Index: 293342 (Open Web Text)

Max Activating Token Index: 96

Text #7

Max Range: 4.5511. Min Range: -4.5511

Max Act: 4.4715. Min Act: -0.1700

Data Index: 146170 (Open Web Text)

Max Activating Token Index: 988

Text #8

Max Range: 4.5511. Min Range: -4.5511

Max Act: 4.4688. Min Act: -0.1700

Data Index: 4240588 (Open Web Text)

Max Activating Token Index: 285

Text #9

Max Range: 4.5511. Min Range: -4.5511

Max Act: 4.4530. Min Act: -0.1700

Data Index: 3606151 (Open Web Text)

Max Activating Token Index: 930

Text #10

Max Range: 4.5511. Min Range: -4.5511

Max Act: 4.4351. Min Act: -0.1700

Data Index: 8439898 (Open Web Text)

Max Activating Token Index: 425

Text #11

Max Range: 4.5511. Min Range: -4.5511

Max Act: 4.4635. Min Act: -0.1700

Data Index: 5846818 (Open Web Text)

Max Activating Token Index: 626

Text #12

Max Range: 4.5511. Min Range: -4.5511

Max Act: 4.4493. Min Act: -0.1700

Data Index: 361526 (Open Web Text)

Max Activating Token Index: 901

Text #13

Max Range: 4.5511. Min Range: -4.5511

Max Act: 4.4393. Min Act: -0.1700

Data Index: 2395057 (Open Web Text)

Max Activating Token Index: 401

Text #14

Max Range: 4.5511. Min Range: -4.5511

Max Act: 4.4213. Min Act: -0.1700

Data Index: 7335829 (Open Web Text)

Max Activating Token Index: 17

Text #15

Max Range: 4.5511. Min Range: -4.5511

Max Act: 4.4024. Min Act: -0.1700

Data Index: 5233464 (Open Web Text)

Max Activating Token Index: 1018

Text #16

Max Range: 4.5511. Min Range: -4.5511

Max Act: 4.4100. Min Act: -0.1700

Data Index: 3729395 (Open Web Text)

Max Activating Token Index: 720

Text #17

Max Range: 4.5511. Min Range: -4.5511

Max Act: 4.4022. Min Act: -0.1700

Data Index: 7034219 (Open Web Text)

Max Activating Token Index: 431

Text #18

Max Range: 4.5511. Min Range: -4.5511

Max Act: 4.4071. Min Act: -0.1700

Data Index: 1064264 (Open Web Text)

Max Activating Token Index: 617

Text #19

Max Range: 4.5511. Min Range: -4.5511

Max Act: 4.4088. Min Act: -0.1700

Data Index: 2123358 (Open Web Text)

Max Activating Token Index: 712