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

Dataset: Open Web Text

Neuron 2232 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: 1.7596. Min Range: -1.7596

Max Act: 1.7596. Min Act: -0.1700

Data Index: 2499217 (Open Web Text)

Max Activating Token Index: 34

Text #1

Max Range: 1.7596. Min Range: -1.7596

Max Act: 1.7076. Min Act: -0.1700

Data Index: 3837833 (Open Web Text)

Max Activating Token Index: 22

Text #2

Max Range: 1.7596. Min Range: -1.7596

Max Act: 1.6675. Min Act: -0.1700

Data Index: 8672914 (Open Web Text)

Max Activating Token Index: 102

Text #3

Max Range: 1.7596. Min Range: -1.7596

Max Act: 1.6481. Min Act: -0.1700

Data Index: 565114 (Open Web Text)

Max Activating Token Index: 25

Text #4

Max Range: 1.7596. Min Range: -1.7596

Max Act: 1.6329. Min Act: -0.1700

Data Index: 5034673 (Open Web Text)

Max Activating Token Index: 333

Text #5

Max Range: 1.7596. Min Range: -1.7596

Max Act: 1.6353. Min Act: -0.1700

Data Index: 3253542 (Open Web Text)

Max Activating Token Index: 55

Text #6

Max Range: 1.7596. Min Range: -1.7596

Max Act: 1.6349. Min Act: -0.1700

Data Index: 4145446 (Open Web Text)

Max Activating Token Index: 22

Text #7

Max Range: 1.7596. Min Range: -1.7596

Max Act: 1.6368. Min Act: -0.1700

Data Index: 6160057 (Open Web Text)

Max Activating Token Index: 610

Text #8

Max Range: 1.7596. Min Range: -1.7596

Max Act: 1.6293. Min Act: -0.1698

Data Index: 2153641 (Open Web Text)

Max Activating Token Index: 46

Text #9

Max Range: 1.7596. Min Range: -1.7596

Max Act: 1.6243. Min Act: -0.1700

Data Index: 3333137 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 1.7596. Min Range: -1.7596

Max Act: 1.6242. Min Act: -0.1700

Data Index: 3228508 (Open Web Text)

Max Activating Token Index: 35

Text #11

Max Range: 1.7596. Min Range: -1.7596

Max Act: 1.6170. Min Act: -0.1700

Data Index: 4507269 (Open Web Text)

Max Activating Token Index: 282

Text #12

Max Range: 1.7596. Min Range: -1.7596

Max Act: 1.6129. Min Act: -0.1700

Data Index: 2223096 (Open Web Text)

Max Activating Token Index: 668

Text #13

Max Range: 1.7596. Min Range: -1.7596

Max Act: 1.6122. Min Act: -0.1700

Data Index: 998280 (Open Web Text)

Max Activating Token Index: 469

Text #14

Max Range: 1.7596. Min Range: -1.7596

Max Act: 1.6136. Min Act: -0.1694

Data Index: 4700035 (Open Web Text)

Max Activating Token Index: 339

Text #15

Max Range: 1.7596. Min Range: -1.7596

Max Act: 1.6117. Min Act: -0.1700

Data Index: 4877776 (Open Web Text)

Max Activating Token Index: 233

Text #16

Max Range: 1.7596. Min Range: -1.7596

Max Act: 1.6060. Min Act: -0.1700

Data Index: 4292586 (Open Web Text)

Max Activating Token Index: 677

Text #17

Max Range: 1.7596. Min Range: -1.7596

Max Act: 1.5997. Min Act: -0.1700

Data Index: 8610094 (Open Web Text)

Max Activating Token Index: 655

Text #18

Max Range: 1.7596. Min Range: -1.7596

Max Act: 1.6005. Min Act: -0.1700

Data Index: 8811433 (Open Web Text)

Max Activating Token Index: 755

Text #19

Max Range: 1.7596. Min Range: -1.7596

Max Act: 1.5951. Min Act: -0.1700

Data Index: 6470859 (Open Web Text)

Max Activating Token Index: 664