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

Dataset: Open Web Text

Neuron 2299 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: 1.0762. Min Range: -1.0762

Max Act: 1.0701. Min Act: -0.1535

Data Index: 6071564 (Open Web Text)

Max Activating Token Index: 1021

Text #1

Max Range: 1.0762. Min Range: -1.0762

Max Act: 1.0665. Min Act: -0.1535

Data Index: 5908974 (Open Web Text)

Max Activating Token Index: 1020

Text #2

Max Range: 1.0762. Min Range: -1.0762

Max Act: 1.0762. Min Act: -0.1535

Data Index: 5176810 (Open Web Text)

Max Activating Token Index: 998

Text #3

Max Range: 1.0762. Min Range: -1.0762

Max Act: 1.0493. Min Act: -0.1535

Data Index: 4855665 (Open Web Text)

Max Activating Token Index: 995

Text #4

Max Range: 1.0762. Min Range: -1.0762

Max Act: 1.0597. Min Act: -0.1535

Data Index: 8189636 (Open Web Text)

Max Activating Token Index: 989

Text #5

Max Range: 1.0762. Min Range: -1.0762

Max Act: 1.0530. Min Act: -0.1555

Data Index: 1509750 (Open Web Text)

Max Activating Token Index: 990

Text #6

Max Range: 1.0762. Min Range: -1.0762

Max Act: 1.0540. Min Act: -0.1535

Data Index: 3237296 (Open Web Text)

Max Activating Token Index: 952

Text #7

Max Range: 1.0762. Min Range: -1.0762

Max Act: 1.0495. Min Act: -0.1535

Data Index: 257525 (Open Web Text)

Max Activating Token Index: 968

Text #8

Max Range: 1.0762. Min Range: -1.0762

Max Act: 1.0482. Min Act: -0.1535

Data Index: 414062 (Open Web Text)

Max Activating Token Index: 1021

Text #9

Max Range: 1.0762. Min Range: -1.0762

Max Act: 1.0465. Min Act: -0.1535

Data Index: 4065744 (Open Web Text)

Max Activating Token Index: 977

Text #10

Max Range: 1.0762. Min Range: -1.0762

Max Act: 1.0488. Min Act: -0.1535

Data Index: 766835 (Open Web Text)

Max Activating Token Index: 1003

Text #11

Max Range: 1.0762. Min Range: -1.0762

Max Act: 1.0424. Min Act: -0.1535

Data Index: 4862128 (Open Web Text)

Max Activating Token Index: 1009

Text #12

Max Range: 1.0762. Min Range: -1.0762

Max Act: 1.0418. Min Act: -0.1535

Data Index: 7113835 (Open Web Text)

Max Activating Token Index: 1000

Text #13

Max Range: 1.0762. Min Range: -1.0762

Max Act: 1.0380. Min Act: -0.1535

Data Index: 2830745 (Open Web Text)

Max Activating Token Index: 221

Text #14

Max Range: 1.0762. Min Range: -1.0762

Max Act: 1.0333. Min Act: -0.1535

Data Index: 319799 (Open Web Text)

Max Activating Token Index: 977

Text #15

Max Range: 1.0762. Min Range: -1.0762

Max Act: 1.0298. Min Act: -0.1535

Data Index: 844440 (Open Web Text)

Max Activating Token Index: 828

Text #16

Max Range: 1.0762. Min Range: -1.0762

Max Act: 1.0288. Min Act: -0.1535

Data Index: 549892 (Open Web Text)

Max Activating Token Index: 994

Text #17

Max Range: 1.0762. Min Range: -1.0762

Max Act: 1.0312. Min Act: -0.1535

Data Index: 4405918 (Open Web Text)

Max Activating Token Index: 963

Text #18

Max Range: 1.0762. Min Range: -1.0762

Max Act: 1.0270. Min Act: -0.1535

Data Index: 1162696 (Open Web Text)

Max Activating Token Index: 967

Text #19

Max Range: 1.0762. Min Range: -1.0762

Max Act: 1.0299. Min Act: -0.1535

Data Index: 6934737 (Open Web Text)

Max Activating Token Index: 958