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

Dataset: Open Web Text

Neuron 1438 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: 3.8309. Min Range: -3.8309

Max Act: 3.8309. Min Act: -0.1700

Data Index: 4116607 (Open Web Text)

Max Activating Token Index: 779

Text #1

Max Range: 3.8309. Min Range: -3.8309

Max Act: 3.7570. Min Act: -0.1700

Data Index: 3805007 (Open Web Text)

Max Activating Token Index: 1017

Text #2

Max Range: 3.8309. Min Range: -3.8309

Max Act: 3.7591. Min Act: -0.1700

Data Index: 789609 (Open Web Text)

Max Activating Token Index: 882

Text #3

Max Range: 3.8309. Min Range: -3.8309

Max Act: 3.7685. Min Act: -0.1700

Data Index: 3572279 (Open Web Text)

Max Activating Token Index: 547

Text #4

Max Range: 3.8309. Min Range: -3.8309

Max Act: 3.7696. Min Act: -0.1700

Data Index: 5981775 (Open Web Text)

Max Activating Token Index: 967

Text #5

Max Range: 3.8309. Min Range: -3.8309

Max Act: 3.7486. Min Act: -0.1700

Data Index: 7675732 (Open Web Text)

Max Activating Token Index: 960

Text #6

Max Range: 3.8309. Min Range: -3.8309

Max Act: 3.6797. Min Act: -0.1700

Data Index: 3396180 (Open Web Text)

Max Activating Token Index: 838

Text #7

Max Range: 3.8309. Min Range: -3.8309

Max Act: 3.6615. Min Act: -0.1700

Data Index: 4234288 (Open Web Text)

Max Activating Token Index: 749

Text #8

Max Range: 3.8309. Min Range: -3.8309

Max Act: 3.6609. Min Act: -0.1700

Data Index: 2851877 (Open Web Text)

Max Activating Token Index: 1010

Text #9

Max Range: 3.8309. Min Range: -3.8309

Max Act: 3.6687. Min Act: -0.1700

Data Index: 4858959 (Open Web Text)

Max Activating Token Index: 936

Text #10

Max Range: 3.8309. Min Range: -3.8309

Max Act: 3.6317. Min Act: -0.1700

Data Index: 6436139 (Open Web Text)

Max Activating Token Index: 699

Text #11

Max Range: 3.8309. Min Range: -3.8309

Max Act: 3.6717. Min Act: -0.1700

Data Index: 4895352 (Open Web Text)

Max Activating Token Index: 788

Text #12

Max Range: 3.8309. Min Range: -3.8309

Max Act: 3.6202. Min Act: -0.1700

Data Index: 4119831 (Open Web Text)

Max Activating Token Index: 448

Text #13

Max Range: 3.8309. Min Range: -3.8309

Max Act: 3.6242. Min Act: -0.1700

Data Index: 1853790 (Open Web Text)

Max Activating Token Index: 720

Text #14

Max Range: 3.8309. Min Range: -3.8309

Max Act: 3.5876. Min Act: -0.1700

Data Index: 1931757 (Open Web Text)

Max Activating Token Index: 951

Text #15

Max Range: 3.8309. Min Range: -3.8309

Max Act: 3.6422. Min Act: -0.1700

Data Index: 6138002 (Open Web Text)

Max Activating Token Index: 963

Text #16

Max Range: 3.8309. Min Range: -3.8309

Max Act: 3.6424. Min Act: -0.1700

Data Index: 5289205 (Open Web Text)

Max Activating Token Index: 653

Text #17

Max Range: 3.8309. Min Range: -3.8309

Max Act: 3.6285. Min Act: -0.1700

Data Index: 656544 (Open Web Text)

Max Activating Token Index: 756

Text #18

Max Range: 3.8309. Min Range: -3.8309

Max Act: 3.6177. Min Act: -0.1700

Data Index: 1144120 (Open Web Text)

Max Activating Token Index: 768

Text #19

Max Range: 3.8309. Min Range: -3.8309

Max Act: 3.6066. Min Act: -0.1700

Data Index: 3635632 (Open Web Text)

Max Activating Token Index: 607