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

Dataset: Open Web Text

Neuron 2156 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: 1.9141. Min Range: -1.9141

Max Act: 1.9141. Min Act: -0.1700

Data Index: 7542109 (Open Web Text)

Max Activating Token Index: 722

Text #1

Max Range: 1.9141. Min Range: -1.9141

Max Act: 1.9106. Min Act: -0.1700

Data Index: 4386423 (Open Web Text)

Max Activating Token Index: 193

Text #2

Max Range: 1.9141. Min Range: -1.9141

Max Act: 1.8976. Min Act: -0.1700

Data Index: 5742639 (Open Web Text)

Max Activating Token Index: 949

Text #3

Max Range: 1.9141. Min Range: -1.9141

Max Act: 1.8674. Min Act: -0.1700

Data Index: 3354649 (Open Web Text)

Max Activating Token Index: 473

Text #4

Max Range: 1.9141. Min Range: -1.9141

Max Act: 1.8676. Min Act: -0.1700

Data Index: 6144828 (Open Web Text)

Max Activating Token Index: 653

Text #5

Max Range: 1.9141. Min Range: -1.9141

Max Act: 1.8749. Min Act: -0.1700

Data Index: 4727708 (Open Web Text)

Max Activating Token Index: 392

Text #6

Max Range: 1.9141. Min Range: -1.9141

Max Act: 1.8690. Min Act: -0.1700

Data Index: 3532587 (Open Web Text)

Max Activating Token Index: 244

Text #7

Max Range: 1.9141. Min Range: -1.9141

Max Act: 1.8715. Min Act: -0.1700

Data Index: 6811978 (Open Web Text)

Max Activating Token Index: 446

Text #8

Max Range: 1.9141. Min Range: -1.9141

Max Act: 1.8585. Min Act: -0.1700

Data Index: 2954393 (Open Web Text)

Max Activating Token Index: 699

Text #9

Max Range: 1.9141. Min Range: -1.9141

Max Act: 1.8614. Min Act: -0.1700

Data Index: 2150223 (Open Web Text)

Max Activating Token Index: 522

Text #10

Max Range: 1.9141. Min Range: -1.9141

Max Act: 1.8625. Min Act: -0.1700

Data Index: 2500420 (Open Web Text)

Max Activating Token Index: 46

Text #11

Max Range: 1.9141. Min Range: -1.9141

Max Act: 1.8667. Min Act: -0.1700

Data Index: 3141977 (Open Web Text)

Max Activating Token Index: 471

Text #12

Max Range: 1.9141. Min Range: -1.9141

Max Act: 1.8690. Min Act: -0.1700

Data Index: 762561 (Open Web Text)

Max Activating Token Index: 510

Text #13

Max Range: 1.9141. Min Range: -1.9141

Max Act: 1.8680. Min Act: -0.1700

Data Index: 3722381 (Open Web Text)

Max Activating Token Index: 461

Text #14

Max Range: 1.9141. Min Range: -1.9141

Max Act: 1.8624. Min Act: -0.1700

Data Index: 3622682 (Open Web Text)

Max Activating Token Index: 313

Text #15

Max Range: 1.9141. Min Range: -1.9141

Max Act: 1.8673. Min Act: -0.1700

Data Index: 7217923 (Open Web Text)

Max Activating Token Index: 1018

Text #16

Max Range: 1.9141. Min Range: -1.9141

Max Act: 1.8740. Min Act: -0.1700

Data Index: 2371714 (Open Web Text)

Max Activating Token Index: 470

Text #17

Max Range: 1.9141. Min Range: -1.9141

Max Act: 1.8516. Min Act: -0.1700

Data Index: 2254708 (Open Web Text)

Max Activating Token Index: 207

Text #18

Max Range: 1.9141. Min Range: -1.9141

Max Act: 1.8503. Min Act: -0.1700

Data Index: 5167173 (Open Web Text)

Max Activating Token Index: 163

Text #19

Max Range: 1.9141. Min Range: -1.9141

Max Act: 1.8501. Min Act: -0.1700

Data Index: 4875550 (Open Web Text)

Max Activating Token Index: 349