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

Dataset: Open Web Text

Neuron 195 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: 3.3087. Min Range: -3.3087

Max Act: 3.3077. Min Act: -0.1700

Data Index: 7204360 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 3.3087. Min Range: -3.3087

Max Act: 3.3087. Min Act: -0.1700

Data Index: 567027 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.3087. Min Range: -3.3087

Max Act: 3.3004. Min Act: -0.1700

Data Index: 873423 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 3.3087. Min Range: -3.3087

Max Act: 3.2768. Min Act: -0.1700

Data Index: 8447764 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 3.3087. Min Range: -3.3087

Max Act: 3.2703. Min Act: -0.1700

Data Index: 177828 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.3087. Min Range: -3.3087

Max Act: 3.2855. Min Act: -0.1700

Data Index: 7016061 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 3.3087. Min Range: -3.3087

Max Act: 3.2562. Min Act: -0.1700

Data Index: 5267795 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 3.3087. Min Range: -3.3087

Max Act: 3.2638. Min Act: -0.1700

Data Index: 6479460 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 3.3087. Min Range: -3.3087

Max Act: 3.2713. Min Act: -0.1700

Data Index: 5986836 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 3.3087. Min Range: -3.3087

Max Act: 3.2554. Min Act: -0.1700

Data Index: 623469 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 3.3087. Min Range: -3.3087

Max Act: 3.2429. Min Act: -0.1700

Data Index: 2492177 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 3.3087. Min Range: -3.3087

Max Act: 3.2486. Min Act: -0.1700

Data Index: 646347 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 3.3087. Min Range: -3.3087

Max Act: 3.2434. Min Act: -0.1700

Data Index: 1019403 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 3.3087. Min Range: -3.3087

Max Act: 3.2497. Min Act: -0.1700

Data Index: 3119669 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.3087. Min Range: -3.3087

Max Act: 3.2493. Min Act: -0.1700

Data Index: 2821181 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 3.3087. Min Range: -3.3087

Max Act: 3.2300. Min Act: -0.1700

Data Index: 2027943 (Open Web Text)

Max Activating Token Index: 8

Text #16

Max Range: 3.3087. Min Range: -3.3087

Max Act: 3.2253. Min Act: -0.1700

Data Index: 5933708 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 3.3087. Min Range: -3.3087

Max Act: 3.2248. Min Act: -0.1700

Data Index: 1271365 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 3.3087. Min Range: -3.3087

Max Act: 3.2274. Min Act: -0.1700

Data Index: 4541346 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 3.3087. Min Range: -3.3087

Max Act: 3.2316. Min Act: -0.1700

Data Index: 3736208 (Open Web Text)

Max Activating Token Index: 10