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

Dataset: Open Web Text

Neuron 1854 in Layer 3

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: 3.7123. Min Range: -3.7123

Max Act: 3.7123. Min Act: -0.1700

Data Index: 8166570 (Open Web Text)

Max Activating Token Index: 704

Text #1

Max Range: 3.7123. Min Range: -3.7123

Max Act: 3.6696. Min Act: -0.1700

Data Index: 4482159 (Open Web Text)

Max Activating Token Index: 248

Text #2

Max Range: 3.7123. Min Range: -3.7123

Max Act: 3.6187. Min Act: -0.1700

Data Index: 3367198 (Open Web Text)

Max Activating Token Index: 571

Text #3

Max Range: 3.7123. Min Range: -3.7123

Max Act: 3.6262. Min Act: -0.1700

Data Index: 7996080 (Open Web Text)

Max Activating Token Index: 23

Text #4

Max Range: 3.7123. Min Range: -3.7123

Max Act: 3.6296. Min Act: -0.1700

Data Index: 662072 (Open Web Text)

Max Activating Token Index: 19

Text #5

Max Range: 3.7123. Min Range: -3.7123

Max Act: 3.6270. Min Act: -0.1700

Data Index: 1356475 (Open Web Text)

Max Activating Token Index: 985

Text #6

Max Range: 3.7123. Min Range: -3.7123

Max Act: 3.5883. Min Act: -0.1700

Data Index: 8552538 (Open Web Text)

Max Activating Token Index: 196

Text #7

Max Range: 3.7123. Min Range: -3.7123

Max Act: 3.5577. Min Act: -0.1700

Data Index: 7904762 (Open Web Text)

Max Activating Token Index: 796

Text #8

Max Range: 3.7123. Min Range: -3.7123

Max Act: 3.5492. Min Act: -0.1700

Data Index: 5572638 (Open Web Text)

Max Activating Token Index: 367

Text #9

Max Range: 3.7123. Min Range: -3.7123

Max Act: 3.5480. Min Act: -0.1700

Data Index: 8430532 (Open Web Text)

Max Activating Token Index: 84

Text #10

Max Range: 3.7123. Min Range: -3.7123

Max Act: 3.5290. Min Act: -0.1700

Data Index: 3649918 (Open Web Text)

Max Activating Token Index: 19

Text #11

Max Range: 3.7123. Min Range: -3.7123

Max Act: 3.5024. Min Act: -0.1700

Data Index: 869263 (Open Web Text)

Max Activating Token Index: 956

Text #12

Max Range: 3.7123. Min Range: -3.7123

Max Act: 3.5117. Min Act: -0.1700

Data Index: 709665 (Open Web Text)

Max Activating Token Index: 163

Text #13

Max Range: 3.7123. Min Range: -3.7123

Max Act: 3.4877. Min Act: -0.1700

Data Index: 4660746 (Open Web Text)

Max Activating Token Index: 380

Text #14

Max Range: 3.7123. Min Range: -3.7123

Max Act: 3.5101. Min Act: -0.1700

Data Index: 8341299 (Open Web Text)

Max Activating Token Index: 445

Text #15

Max Range: 3.7123. Min Range: -3.7123

Max Act: 3.4922. Min Act: -0.1700

Data Index: 1172644 (Open Web Text)

Max Activating Token Index: 47

Text #16

Max Range: 3.7123. Min Range: -3.7123

Max Act: 3.4790. Min Act: -0.1700

Data Index: 6506003 (Open Web Text)

Max Activating Token Index: 433

Text #17

Max Range: 3.7123. Min Range: -3.7123

Max Act: 3.4716. Min Act: -0.1700

Data Index: 3618451 (Open Web Text)

Max Activating Token Index: 833

Text #18

Max Range: 3.7123. Min Range: -3.7123

Max Act: 3.4895. Min Act: -0.1700

Data Index: 4558548 (Open Web Text)

Max Activating Token Index: 965

Text #19

Max Range: 3.7123. Min Range: -3.7123

Max Act: 3.4699. Min Act: -0.1700

Data Index: 1147887 (Open Web Text)

Max Activating Token Index: 484