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

Dataset: Open Web Text

Neuron 89 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: 1.5401. Min Range: -1.5401

Max Act: 1.5401. Min Act: -0.1700

Data Index: 2289853 (Open Web Text)

Max Activating Token Index: 487

Text #1

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.4894. Min Act: -0.1700

Data Index: 2231514 (Open Web Text)

Max Activating Token Index: 601

Text #2

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.4736. Min Act: -0.1700

Data Index: 3920401 (Open Web Text)

Max Activating Token Index: 829

Text #3

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.4776. Min Act: -0.1700

Data Index: 1521685 (Open Web Text)

Max Activating Token Index: 422

Text #4

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.4679. Min Act: -0.1700

Data Index: 8434734 (Open Web Text)

Max Activating Token Index: 121

Text #5

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.4560. Min Act: -0.1700

Data Index: 7171306 (Open Web Text)

Max Activating Token Index: 540

Text #6

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.4554. Min Act: -0.1700

Data Index: 1616198 (Open Web Text)

Max Activating Token Index: 40

Text #7

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.4260. Min Act: -0.1700

Data Index: 2995487 (Open Web Text)

Max Activating Token Index: 745

Text #8

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.4395. Min Act: -0.1700

Data Index: 2274204 (Open Web Text)

Max Activating Token Index: 79

Text #9

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.4303. Min Act: -0.1700

Data Index: 5370501 (Open Web Text)

Max Activating Token Index: 941

Text #10

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.4178. Min Act: -0.1700

Data Index: 3141774 (Open Web Text)

Max Activating Token Index: 157

Text #11

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.4285. Min Act: -0.1700

Data Index: 8539796 (Open Web Text)

Max Activating Token Index: 451

Text #12

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.4160. Min Act: -0.1700

Data Index: 7858258 (Open Web Text)

Max Activating Token Index: 727

Text #13

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.3993. Min Act: -0.1700

Data Index: 5294392 (Open Web Text)

Max Activating Token Index: 552

Text #14

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.4119. Min Act: -0.1700

Data Index: 7810011 (Open Web Text)

Max Activating Token Index: 1012

Text #15

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.4002. Min Act: -0.1700

Data Index: 4280156 (Open Web Text)

Max Activating Token Index: 606

Text #16

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.4122. Min Act: -0.1700

Data Index: 6908466 (Open Web Text)

Max Activating Token Index: 698

Text #17

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.4014. Min Act: -0.1700

Data Index: 1343686 (Open Web Text)

Max Activating Token Index: 268

Text #18

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.4128. Min Act: -0.1700

Data Index: 135260 (Open Web Text)

Max Activating Token Index: 977

Text #19

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.3954. Min Act: -0.1700

Data Index: 1747028 (Open Web Text)

Max Activating Token Index: 425