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

Dataset: Open Web Text

Neuron 2891 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: 3.5115. Min Range: -3.5115

Max Act: 3.5115. Min Act: -0.1700

Data Index: 3654750 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 3.5115. Min Range: -3.5115

Max Act: 3.4213. Min Act: -0.1700

Data Index: 6742457 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 3.5115. Min Range: -3.5115

Max Act: 3.3648. Min Act: -0.1700

Data Index: 2476474 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 3.5115. Min Range: -3.5115

Max Act: 3.1387. Min Act: -0.1700

Data Index: 1894422 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 3.5115. Min Range: -3.5115

Max Act: 3.0786. Min Act: -0.1700

Data Index: 7545268 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 3.5115. Min Range: -3.5115

Max Act: 3.0198. Min Act: -0.1700

Data Index: 2394797 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 3.5115. Min Range: -3.5115

Max Act: 2.9974. Min Act: -0.1700

Data Index: 560712 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 3.5115. Min Range: -3.5115

Max Act: 2.9590. Min Act: -0.1700

Data Index: 5536180 (Open Web Text)

Max Activating Token Index: 376

Text #8

Max Range: 3.5115. Min Range: -3.5115

Max Act: 2.9281. Min Act: -0.1700

Data Index: 7531971 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 3.5115. Min Range: -3.5115

Max Act: 2.9253. Min Act: -0.1700

Data Index: 3026196 (Open Web Text)

Max Activating Token Index: 702

Text #10

Max Range: 3.5115. Min Range: -3.5115

Max Act: 2.8992. Min Act: -0.1700

Data Index: 2407858 (Open Web Text)

Max Activating Token Index: 84

Text #11

Max Range: 3.5115. Min Range: -3.5115

Max Act: 2.8486. Min Act: -0.1700

Data Index: 8647852 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 3.5115. Min Range: -3.5115

Max Act: 2.8364. Min Act: -0.1700

Data Index: 4934676 (Open Web Text)

Max Activating Token Index: 382

Text #13

Max Range: 3.5115. Min Range: -3.5115

Max Act: 2.8229. Min Act: -0.1700

Data Index: 7826775 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 3.5115. Min Range: -3.5115

Max Act: 2.8240. Min Act: -0.1700

Data Index: 8249809 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 3.5115. Min Range: -3.5115

Max Act: 2.8130. Min Act: -0.1700

Data Index: 3600876 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 3.5115. Min Range: -3.5115

Max Act: 2.8098. Min Act: -0.1700

Data Index: 3377447 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 3.5115. Min Range: -3.5115

Max Act: 2.8103. Min Act: -0.1700

Data Index: 5770384 (Open Web Text)

Max Activating Token Index: 648

Text #18

Max Range: 3.5115. Min Range: -3.5115

Max Act: 2.7843. Min Act: -0.1700

Data Index: 5589395 (Open Web Text)

Max Activating Token Index: 240

Text #19

Max Range: 3.5115. Min Range: -3.5115

Max Act: 2.7754. Min Act: -0.1700

Data Index: 154690 (Open Web Text)

Max Activating Token Index: 239