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

Dataset: Open Web Text

Neuron 2174 in Layer 5

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: 3.1202. Min Range: -3.1202

Max Act: 3.0713. Min Act: -0.1700

Data Index: 2213126 (Open Web Text)

Max Activating Token Index: 963

Text #1

Max Range: 3.1202. Min Range: -3.1202

Max Act: 3.1202. Min Act: -0.1700

Data Index: 1707402 (Open Web Text)

Max Activating Token Index: 968

Text #2

Max Range: 3.1202. Min Range: -3.1202

Max Act: 3.0943. Min Act: -0.1700

Data Index: 1453936 (Open Web Text)

Max Activating Token Index: 771

Text #3

Max Range: 3.1202. Min Range: -3.1202

Max Act: 3.0648. Min Act: -0.1700

Data Index: 2944608 (Open Web Text)

Max Activating Token Index: 660

Text #4

Max Range: 3.1202. Min Range: -3.1202

Max Act: 3.0304. Min Act: -0.1700

Data Index: 7723136 (Open Web Text)

Max Activating Token Index: 711

Text #5

Max Range: 3.1202. Min Range: -3.1202

Max Act: 3.0178. Min Act: -0.1700

Data Index: 4693496 (Open Web Text)

Max Activating Token Index: 108

Text #6

Max Range: 3.1202. Min Range: -3.1202

Max Act: 3.0180. Min Act: -0.1700

Data Index: 7891855 (Open Web Text)

Max Activating Token Index: 489

Text #7

Max Range: 3.1202. Min Range: -3.1202

Max Act: 2.9932. Min Act: -0.1700

Data Index: 319390 (Open Web Text)

Max Activating Token Index: 477

Text #8

Max Range: 3.1202. Min Range: -3.1202

Max Act: 3.0026. Min Act: -0.1700

Data Index: 495003 (Open Web Text)

Max Activating Token Index: 569

Text #9

Max Range: 3.1202. Min Range: -3.1202

Max Act: 2.9793. Min Act: -0.1700

Data Index: 7667590 (Open Web Text)

Max Activating Token Index: 61

Text #10

Max Range: 3.1202. Min Range: -3.1202

Max Act: 2.9808. Min Act: -0.1700

Data Index: 4354364 (Open Web Text)

Max Activating Token Index: 569

Text #11

Max Range: 3.1202. Min Range: -3.1202

Max Act: 2.9724. Min Act: -0.1700

Data Index: 3924215 (Open Web Text)

Max Activating Token Index: 65

Text #12

Max Range: 3.1202. Min Range: -3.1202

Max Act: 2.9845. Min Act: -0.1700

Data Index: 7367023 (Open Web Text)

Max Activating Token Index: 85

Text #13

Max Range: 3.1202. Min Range: -3.1202

Max Act: 2.9828. Min Act: -0.1700

Data Index: 7898361 (Open Web Text)

Max Activating Token Index: 489

Text #14

Max Range: 3.1202. Min Range: -3.1202

Max Act: 2.9858. Min Act: -0.1700

Data Index: 535436 (Open Web Text)

Max Activating Token Index: 677

Text #15

Max Range: 3.1202. Min Range: -3.1202

Max Act: 2.9723. Min Act: -0.1700

Data Index: 3134485 (Open Web Text)

Max Activating Token Index: 611

Text #16

Max Range: 3.1202. Min Range: -3.1202

Max Act: 2.9395. Min Act: -0.1700

Data Index: 6626770 (Open Web Text)

Max Activating Token Index: 621

Text #17

Max Range: 3.1202. Min Range: -3.1202

Max Act: 2.9968. Min Act: -0.1700

Data Index: 2223749 (Open Web Text)

Max Activating Token Index: 543

Text #18

Max Range: 3.1202. Min Range: -3.1202

Max Act: 2.9744. Min Act: -0.1700

Data Index: 2037170 (Open Web Text)

Max Activating Token Index: 524

Text #19

Max Range: 3.1202. Min Range: -3.1202

Max Act: 2.9666. Min Act: -0.1700

Data Index: 4590655 (Open Web Text)

Max Activating Token Index: 385