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

Dataset: Open Web Text

Neuron 778 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: 2.6085. Min Range: -2.6085

Max Act: 2.6085. Min Act: -0.1700

Data Index: 8427306 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 2.6085. Min Range: -2.6085

Max Act: 2.5754. Min Act: -0.1700

Data Index: 5965553 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 2.6085. Min Range: -2.6085

Max Act: 2.5543. Min Act: -0.1700

Data Index: 6658166 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 2.6085. Min Range: -2.6085

Max Act: 2.5538. Min Act: -0.1700

Data Index: 2229062 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 2.6085. Min Range: -2.6085

Max Act: 2.5534. Min Act: -0.1700

Data Index: 3996149 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 2.6085. Min Range: -2.6085

Max Act: 2.5554. Min Act: -0.1700

Data Index: 4339424 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 2.6085. Min Range: -2.6085

Max Act: 2.5534. Min Act: -0.1700

Data Index: 8362304 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 2.6085. Min Range: -2.6085

Max Act: 2.5375. Min Act: -0.1700

Data Index: 2155003 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 2.6085. Min Range: -2.6085

Max Act: 2.5373. Min Act: -0.1700

Data Index: 2561101 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 2.6085. Min Range: -2.6085

Max Act: 2.5473. Min Act: -0.1700

Data Index: 1752554 (Open Web Text)

Max Activating Token Index: 13

Text #10

Max Range: 2.6085. Min Range: -2.6085

Max Act: 2.5318. Min Act: -0.1700

Data Index: 4468025 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 2.6085. Min Range: -2.6085

Max Act: 2.5271. Min Act: -0.1700

Data Index: 8035352 (Open Web Text)

Max Activating Token Index: 486

Text #12

Max Range: 2.6085. Min Range: -2.6085

Max Act: 2.5372. Min Act: -0.1700

Data Index: 7027547 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 2.6085. Min Range: -2.6085

Max Act: 2.5177. Min Act: -0.1700

Data Index: 2395939 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 2.6085. Min Range: -2.6085

Max Act: 2.5153. Min Act: -0.1700

Data Index: 1662393 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 2.6085. Min Range: -2.6085

Max Act: 2.5165. Min Act: -0.1700

Data Index: 1932039 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 2.6085. Min Range: -2.6085

Max Act: 2.5064. Min Act: -0.1700

Data Index: 3042503 (Open Web Text)

Max Activating Token Index: 1010

Text #17

Max Range: 2.6085. Min Range: -2.6085

Max Act: 2.5104. Min Act: -0.1700

Data Index: 7762329 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 2.6085. Min Range: -2.6085

Max Act: 2.5187. Min Act: -0.1700

Data Index: 6895522 (Open Web Text)

Max Activating Token Index: 18

Text #19

Max Range: 2.6085. Min Range: -2.6085

Max Act: 2.5129. Min Act: -0.1700

Data Index: 6868286 (Open Web Text)

Max Activating Token Index: 4