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

Dataset: Open Web Text

Neuron 2055 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: 6.0169. Min Range: -6.0169

Max Act: 6.0169. Min Act: -0.1700

Data Index: 6695873 (Open Web Text)

Max Activating Token Index: 125

Text #1

Max Range: 6.0169. Min Range: -6.0169

Max Act: 5.8551. Min Act: -0.1700

Data Index: 6424919 (Open Web Text)

Max Activating Token Index: 406

Text #2

Max Range: 6.0169. Min Range: -6.0169

Max Act: 5.6977. Min Act: -0.1700

Data Index: 5273087 (Open Web Text)

Max Activating Token Index: 46

Text #3

Max Range: 6.0169. Min Range: -6.0169

Max Act: 5.6945. Min Act: -0.1700

Data Index: 4019295 (Open Web Text)

Max Activating Token Index: 489

Text #4

Max Range: 6.0169. Min Range: -6.0169

Max Act: 5.5670. Min Act: -0.1700

Data Index: 2706858 (Open Web Text)

Max Activating Token Index: 375

Text #5

Max Range: 6.0169. Min Range: -6.0169

Max Act: 5.4539. Min Act: -0.1700

Data Index: 700784 (Open Web Text)

Max Activating Token Index: 157

Text #6

Max Range: 6.0169. Min Range: -6.0169

Max Act: 5.3263. Min Act: -0.1700

Data Index: 5429848 (Open Web Text)

Max Activating Token Index: 687

Text #7

Max Range: 6.0169. Min Range: -6.0169

Max Act: 5.3888. Min Act: -0.1700

Data Index: 4542039 (Open Web Text)

Max Activating Token Index: 307

Text #8

Max Range: 6.0169. Min Range: -6.0169

Max Act: 5.3178. Min Act: -0.1700

Data Index: 3858783 (Open Web Text)

Max Activating Token Index: 46

Text #9

Max Range: 6.0169. Min Range: -6.0169

Max Act: 5.2903. Min Act: -0.1700

Data Index: 5499443 (Open Web Text)

Max Activating Token Index: 467

Text #10

Max Range: 6.0169. Min Range: -6.0169

Max Act: 5.2613. Min Act: -0.1700

Data Index: 2059281 (Open Web Text)

Max Activating Token Index: 902

Text #11

Max Range: 6.0169. Min Range: -6.0169

Max Act: 5.2895. Min Act: -0.1700

Data Index: 3676050 (Open Web Text)

Max Activating Token Index: 945

Text #12

Max Range: 6.0169. Min Range: -6.0169

Max Act: 5.2627. Min Act: -0.1700

Data Index: 431298 (Open Web Text)

Max Activating Token Index: 240

Text #13

Max Range: 6.0169. Min Range: -6.0169

Max Act: 5.2016. Min Act: -0.1700

Data Index: 4201844 (Open Web Text)

Max Activating Token Index: 175

Text #14

Max Range: 6.0169. Min Range: -6.0169

Max Act: 5.2669. Min Act: -0.1700

Data Index: 3643706 (Open Web Text)

Max Activating Token Index: 344

Text #15

Max Range: 6.0169. Min Range: -6.0169

Max Act: 5.2410. Min Act: -0.1700

Data Index: 6270912 (Open Web Text)

Max Activating Token Index: 798

Text #16

Max Range: 6.0169. Min Range: -6.0169

Max Act: 5.1525. Min Act: -0.1700

Data Index: 535310 (Open Web Text)

Max Activating Token Index: 906

Text #17

Max Range: 6.0169. Min Range: -6.0169

Max Act: 5.1925. Min Act: -0.1700

Data Index: 8477662 (Open Web Text)

Max Activating Token Index: 27

Text #18

Max Range: 6.0169. Min Range: -6.0169

Max Act: 5.1918. Min Act: -0.1700

Data Index: 6405467 (Open Web Text)

Max Activating Token Index: 747

Text #19

Max Range: 6.0169. Min Range: -6.0169

Max Act: 5.1521. Min Act: -0.1700

Data Index: 3017154 (Open Web Text)

Max Activating Token Index: 104