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

Dataset: Open Web Text

Neuron 303 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: 3.0119. Min Range: -3.0119

Max Act: 3.0119. Min Act: -0.1700

Data Index: 7120926 (Open Web Text)

Max Activating Token Index: 22

Text #1

Max Range: 3.0119. Min Range: -3.0119

Max Act: 3.0089. Min Act: -0.1700

Data Index: 8680445 (Open Web Text)

Max Activating Token Index: 73

Text #2

Max Range: 3.0119. Min Range: -3.0119

Max Act: 2.9812. Min Act: -0.1700

Data Index: 6925490 (Open Web Text)

Max Activating Token Index: 116

Text #3

Max Range: 3.0119. Min Range: -3.0119

Max Act: 2.9431. Min Act: -0.1700

Data Index: 4426774 (Open Web Text)

Max Activating Token Index: 35

Text #4

Max Range: 3.0119. Min Range: -3.0119

Max Act: 2.9108. Min Act: -0.1700

Data Index: 7598827 (Open Web Text)

Max Activating Token Index: 84

Text #5

Max Range: 3.0119. Min Range: -3.0119

Max Act: 2.9008. Min Act: -0.1700

Data Index: 5192798 (Open Web Text)

Max Activating Token Index: 27

Text #6

Max Range: 3.0119. Min Range: -3.0119

Max Act: 2.8980. Min Act: -0.1700

Data Index: 5692629 (Open Web Text)

Max Activating Token Index: 126

Text #7

Max Range: 3.0119. Min Range: -3.0119

Max Act: 2.8887. Min Act: -0.1700

Data Index: 3060577 (Open Web Text)

Max Activating Token Index: 32

Text #8

Max Range: 3.0119. Min Range: -3.0119

Max Act: 2.8982. Min Act: -0.1700

Data Index: 5965074 (Open Web Text)

Max Activating Token Index: 15

Text #9

Max Range: 3.0119. Min Range: -3.0119

Max Act: 2.8867. Min Act: -0.1700

Data Index: 8383480 (Open Web Text)

Max Activating Token Index: 1022

Text #10

Max Range: 3.0119. Min Range: -3.0119

Max Act: 2.8830. Min Act: -0.1700

Data Index: 348233 (Open Web Text)

Max Activating Token Index: 84

Text #11

Max Range: 3.0119. Min Range: -3.0119

Max Act: 2.8581. Min Act: -0.1700

Data Index: 6803611 (Open Web Text)

Max Activating Token Index: 543

Text #12

Max Range: 3.0119. Min Range: -3.0119

Max Act: 2.8733. Min Act: -0.1700

Data Index: 917537 (Open Web Text)

Max Activating Token Index: 207

Text #13

Max Range: 3.0119. Min Range: -3.0119

Max Act: 2.8515. Min Act: -0.1700

Data Index: 7284066 (Open Web Text)

Max Activating Token Index: 151

Text #14

Max Range: 3.0119. Min Range: -3.0119

Max Act: 2.8495. Min Act: -0.1700

Data Index: 3860204 (Open Web Text)

Max Activating Token Index: 595

Text #15

Max Range: 3.0119. Min Range: -3.0119

Max Act: 2.8392. Min Act: -0.1700

Data Index: 5434016 (Open Web Text)

Max Activating Token Index: 15

Text #16

Max Range: 3.0119. Min Range: -3.0119

Max Act: 2.8337. Min Act: -0.1700

Data Index: 6645209 (Open Web Text)

Max Activating Token Index: 781

Text #17

Max Range: 3.0119. Min Range: -3.0119

Max Act: 2.8403. Min Act: -0.1700

Data Index: 5909644 (Open Web Text)

Max Activating Token Index: 24

Text #18

Max Range: 3.0119. Min Range: -3.0119

Max Act: 2.8294. Min Act: -0.1700

Data Index: 5040313 (Open Web Text)

Max Activating Token Index: 1018

Text #19

Max Range: 3.0119. Min Range: -3.0119

Max Act: 2.8193. Min Act: -0.1700

Data Index: 3483246 (Open Web Text)

Max Activating Token Index: 493