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

Dataset: Open Web Text

Neuron 1689 in Layer 1

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: 2.0959. Min Range: -2.0959

Max Act: 2.0959. Min Act: -0.1700

Data Index: 8296695 (Open Web Text)

Max Activating Token Index: 10

Text #1

Max Range: 2.0959. Min Range: -2.0959

Max Act: 2.0240. Min Act: -0.1700

Data Index: 6824413 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 2.0959. Min Range: -2.0959

Max Act: 2.0052. Min Act: -0.1700

Data Index: 5523631 (Open Web Text)

Max Activating Token Index: 44

Text #3

Max Range: 2.0959. Min Range: -2.0959

Max Act: 1.9877. Min Act: -0.1700

Data Index: 8343000 (Open Web Text)

Max Activating Token Index: 21

Text #4

Max Range: 2.0959. Min Range: -2.0959

Max Act: 1.9602. Min Act: -0.1700

Data Index: 4455154 (Open Web Text)

Max Activating Token Index: 10

Text #5

Max Range: 2.0959. Min Range: -2.0959

Max Act: 1.9547. Min Act: -0.1700

Data Index: 6541553 (Open Web Text)

Max Activating Token Index: 9

Text #6

Max Range: 2.0959. Min Range: -2.0959

Max Act: 1.9627. Min Act: -0.1700

Data Index: 4667046 (Open Web Text)

Max Activating Token Index: 58

Text #7

Max Range: 2.0959. Min Range: -2.0959

Max Act: 1.9313. Min Act: -0.1700

Data Index: 4535198 (Open Web Text)

Max Activating Token Index: 24

Text #8

Max Range: 2.0959. Min Range: -2.0959

Max Act: 1.9509. Min Act: -0.1700

Data Index: 2888260 (Open Web Text)

Max Activating Token Index: 457

Text #9

Max Range: 2.0959. Min Range: -2.0959

Max Act: 1.9519. Min Act: -0.1700

Data Index: 7852407 (Open Web Text)

Max Activating Token Index: 60

Text #10

Max Range: 2.0959. Min Range: -2.0959

Max Act: 1.9214. Min Act: -0.1700

Data Index: 2716950 (Open Web Text)

Max Activating Token Index: 284

Text #11

Max Range: 2.0959. Min Range: -2.0959

Max Act: 1.9056. Min Act: -0.1700

Data Index: 7210840 (Open Web Text)

Max Activating Token Index: 861

Text #12

Max Range: 2.0959. Min Range: -2.0959

Max Act: 1.9268. Min Act: -0.1700

Data Index: 4953619 (Open Web Text)

Max Activating Token Index: 44

Text #13

Max Range: 2.0959. Min Range: -2.0959

Max Act: 1.9217. Min Act: -0.1700

Data Index: 3532462 (Open Web Text)

Max Activating Token Index: 439

Text #14

Max Range: 2.0959. Min Range: -2.0959

Max Act: 1.9227. Min Act: -0.1700

Data Index: 2619780 (Open Web Text)

Max Activating Token Index: 28

Text #15

Max Range: 2.0959. Min Range: -2.0959

Max Act: 1.9185. Min Act: -0.1700

Data Index: 4569324 (Open Web Text)

Max Activating Token Index: 970

Text #16

Max Range: 2.0959. Min Range: -2.0959

Max Act: 1.9202. Min Act: -0.1700

Data Index: 4542686 (Open Web Text)

Max Activating Token Index: 21

Text #17

Max Range: 2.0959. Min Range: -2.0959

Max Act: 1.8922. Min Act: -0.1700

Data Index: 1190249 (Open Web Text)

Max Activating Token Index: 265

Text #18

Max Range: 2.0959. Min Range: -2.0959

Max Act: 1.8971. Min Act: -0.1700

Data Index: 6824412 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 2.0959. Min Range: -2.0959

Max Act: 1.8824. Min Act: -0.1700

Data Index: 4039649 (Open Web Text)

Max Activating Token Index: 856