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

Dataset: Open Web Text

Neuron 30 in Layer 1

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: 1.7859. Min Range: -1.7859

Max Act: 1.7859. Min Act: -0.1700

Data Index: 1750085 (Open Web Text)

Max Activating Token Index: 12

Text #1

Max Range: 1.7859. Min Range: -1.7859

Max Act: 1.7652. Min Act: -0.1700

Data Index: 7847046 (Open Web Text)

Max Activating Token Index: 341

Text #2

Max Range: 1.7859. Min Range: -1.7859

Max Act: 1.7734. Min Act: -0.1700

Data Index: 782015 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 1.7859. Min Range: -1.7859

Max Act: 1.7530. Min Act: -0.1700

Data Index: 8628452 (Open Web Text)

Max Activating Token Index: 613

Text #4

Max Range: 1.7859. Min Range: -1.7859

Max Act: 1.7348. Min Act: -0.1700

Data Index: 1610377 (Open Web Text)

Max Activating Token Index: 703

Text #5

Max Range: 1.7859. Min Range: -1.7859

Max Act: 1.7248. Min Act: -0.1700

Data Index: 6930509 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 1.7859. Min Range: -1.7859

Max Act: 1.7301. Min Act: -0.1700

Data Index: 4675901 (Open Web Text)

Max Activating Token Index: 326

Text #7

Max Range: 1.7859. Min Range: -1.7859

Max Act: 1.7392. Min Act: -0.1700

Data Index: 7290286 (Open Web Text)

Max Activating Token Index: 10

Text #8

Max Range: 1.7859. Min Range: -1.7859

Max Act: 1.7327. Min Act: -0.1696

Data Index: 2090496 (Open Web Text)

Max Activating Token Index: 832

Text #9

Max Range: 1.7859. Min Range: -1.7859

Max Act: 1.7261. Min Act: -0.1700

Data Index: 3062987 (Open Web Text)

Max Activating Token Index: 908

Text #10

Max Range: 1.7859. Min Range: -1.7859

Max Act: 1.7239. Min Act: -0.1700

Data Index: 1117289 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 1.7859. Min Range: -1.7859

Max Act: 1.7125. Min Act: -0.1700

Data Index: 1964416 (Open Web Text)

Max Activating Token Index: 409

Text #12

Max Range: 1.7859. Min Range: -1.7859

Max Act: 1.7158. Min Act: -0.1675

Data Index: 7916338 (Open Web Text)

Max Activating Token Index: 280

Text #13

Max Range: 1.7859. Min Range: -1.7859

Max Act: 1.7217. Min Act: -0.1700

Data Index: 7534841 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 1.7859. Min Range: -1.7859

Max Act: 1.7259. Min Act: -0.1700

Data Index: 5922813 (Open Web Text)

Max Activating Token Index: 446

Text #15

Max Range: 1.7859. Min Range: -1.7859

Max Act: 1.7107. Min Act: -0.1700

Data Index: 3962424 (Open Web Text)

Max Activating Token Index: 843

Text #16

Max Range: 1.7859. Min Range: -1.7859

Max Act: 1.7198. Min Act: -0.1700

Data Index: 3687447 (Open Web Text)

Max Activating Token Index: 280

Text #17

Max Range: 1.7859. Min Range: -1.7859

Max Act: 1.7175. Min Act: -0.1700

Data Index: 6812112 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 1.7859. Min Range: -1.7859

Max Act: 1.7145. Min Act: -0.1700

Data Index: 1022547 (Open Web Text)

Max Activating Token Index: 340

Text #19

Max Range: 1.7859. Min Range: -1.7859

Max Act: 1.7126. Min Act: -0.1700

Data Index: 4375801 (Open Web Text)

Max Activating Token Index: 209