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

Dataset: Open Web Text

Neuron 116 in Layer 0

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: 4.8089. Min Range: -4.8089

Max Act: 4.8089. Min Act: -0.1700

Data Index: 8403580 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 4.8089. Min Range: -4.8089

Max Act: 4.7508. Min Act: -0.1700

Data Index: 587288 (Open Web Text)

Max Activating Token Index: 24

Text #2

Max Range: 4.8089. Min Range: -4.8089

Max Act: 4.7272. Min Act: -0.1700

Data Index: 5763712 (Open Web Text)

Max Activating Token Index: 87

Text #3

Max Range: 4.8089. Min Range: -4.8089

Max Act: 4.7358. Min Act: -0.1700

Data Index: 149009 (Open Web Text)

Max Activating Token Index: 34

Text #4

Max Range: 4.8089. Min Range: -4.8089

Max Act: 4.6809. Min Act: -0.1700

Data Index: 6212708 (Open Web Text)

Max Activating Token Index: 16

Text #5

Max Range: 4.8089. Min Range: -4.8089

Max Act: 4.7060. Min Act: -0.1700

Data Index: 4557870 (Open Web Text)

Max Activating Token Index: 819

Text #6

Max Range: 4.8089. Min Range: -4.8089

Max Act: 4.7076. Min Act: -0.1700

Data Index: 6299431 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 4.8089. Min Range: -4.8089

Max Act: 4.6821. Min Act: -0.1700

Data Index: 2653094 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 4.8089. Min Range: -4.8089

Max Act: 4.6710. Min Act: -0.1700

Data Index: 6758917 (Open Web Text)

Max Activating Token Index: 366

Text #9

Max Range: 4.8089. Min Range: -4.8089

Max Act: 4.6644. Min Act: -0.1700

Data Index: 8035779 (Open Web Text)

Max Activating Token Index: 14

Text #10

Max Range: 4.8089. Min Range: -4.8089

Max Act: 4.6463. Min Act: -0.1700

Data Index: 3302376 (Open Web Text)

Max Activating Token Index: 28

Text #11

Max Range: 4.8089. Min Range: -4.8089

Max Act: 4.6590. Min Act: -0.1700

Data Index: 149010 (Open Web Text)

Max Activating Token Index: 138

Text #12

Max Range: 4.8089. Min Range: -4.8089

Max Act: 4.6699. Min Act: -0.1700

Data Index: 6958148 (Open Web Text)

Max Activating Token Index: 244

Text #13

Max Range: 4.8089. Min Range: -4.8089

Max Act: 4.6486. Min Act: -0.1700

Data Index: 1506129 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 4.8089. Min Range: -4.8089

Max Act: 4.6391. Min Act: -0.1700

Data Index: 7890712 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 4.8089. Min Range: -4.8089

Max Act: 4.6301. Min Act: -0.1700

Data Index: 4595694 (Open Web Text)

Max Activating Token Index: 456

Text #16

Max Range: 4.8089. Min Range: -4.8089

Max Act: 4.6232. Min Act: -0.1700

Data Index: 5034029 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 4.8089. Min Range: -4.8089

Max Act: 4.6403. Min Act: -0.1700

Data Index: 1992041 (Open Web Text)

Max Activating Token Index: 41

Text #18

Max Range: 4.8089. Min Range: -4.8089

Max Act: 4.6304. Min Act: -0.1700

Data Index: 7051313 (Open Web Text)

Max Activating Token Index: 24

Text #19

Max Range: 4.8089. Min Range: -4.8089

Max Act: 4.6217. Min Act: -0.1700

Data Index: 2293946 (Open Web Text)

Max Activating Token Index: 4