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

Dataset: Open Web Text

Neuron 2214 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: 3.9867. Min Range: -3.9867

Max Act: 3.9867. Min Act: -0.1700

Data Index: 7956430 (Open Web Text)

Max Activating Token Index: 989

Text #1

Max Range: 3.9867. Min Range: -3.9867

Max Act: 3.8361. Min Act: -0.1700

Data Index: 1837567 (Open Web Text)

Max Activating Token Index: 284

Text #2

Max Range: 3.9867. Min Range: -3.9867

Max Act: 3.7370. Min Act: -0.1700

Data Index: 4368034 (Open Web Text)

Max Activating Token Index: 485

Text #3

Max Range: 3.9867. Min Range: -3.9867

Max Act: 3.7318. Min Act: -0.1700

Data Index: 2442386 (Open Web Text)

Max Activating Token Index: 800

Text #4

Max Range: 3.9867. Min Range: -3.9867

Max Act: 3.7161. Min Act: -0.1700

Data Index: 4296585 (Open Web Text)

Max Activating Token Index: 29

Text #5

Max Range: 3.9867. Min Range: -3.9867

Max Act: 3.6649. Min Act: -0.1700

Data Index: 5724852 (Open Web Text)

Max Activating Token Index: 661

Text #6

Max Range: 3.9867. Min Range: -3.9867

Max Act: 3.6406. Min Act: -0.1700

Data Index: 2798932 (Open Web Text)

Max Activating Token Index: 58

Text #7

Max Range: 3.9867. Min Range: -3.9867

Max Act: 3.6293. Min Act: -0.1700

Data Index: 4222158 (Open Web Text)

Max Activating Token Index: 824

Text #8

Max Range: 3.9867. Min Range: -3.9867

Max Act: 3.6477. Min Act: -0.1700

Data Index: 1629735 (Open Web Text)

Max Activating Token Index: 315

Text #9

Max Range: 3.9867. Min Range: -3.9867

Max Act: 3.6353. Min Act: -0.1700

Data Index: 6290183 (Open Web Text)

Max Activating Token Index: 721

Text #10

Max Range: 3.9867. Min Range: -3.9867

Max Act: 3.5986. Min Act: -0.1700

Data Index: 967869 (Open Web Text)

Max Activating Token Index: 115

Text #11

Max Range: 3.9867. Min Range: -3.9867

Max Act: 3.5724. Min Act: -0.1700

Data Index: 471661 (Open Web Text)

Max Activating Token Index: 630

Text #12

Max Range: 3.9867. Min Range: -3.9867

Max Act: 3.5917. Min Act: -0.1700

Data Index: 3937051 (Open Web Text)

Max Activating Token Index: 908

Text #13

Max Range: 3.9867. Min Range: -3.9867

Max Act: 3.5672. Min Act: -0.1700

Data Index: 388865 (Open Web Text)

Max Activating Token Index: 352

Text #14

Max Range: 3.9867. Min Range: -3.9867

Max Act: 3.5566. Min Act: -0.1700

Data Index: 1151200 (Open Web Text)

Max Activating Token Index: 165

Text #15

Max Range: 3.9867. Min Range: -3.9867

Max Act: 3.5869. Min Act: -0.1700

Data Index: 2814682 (Open Web Text)

Max Activating Token Index: 54

Text #16

Max Range: 3.9867. Min Range: -3.9867

Max Act: 3.5762. Min Act: -0.1700

Data Index: 4404730 (Open Web Text)

Max Activating Token Index: 710

Text #17

Max Range: 3.9867. Min Range: -3.9867

Max Act: 3.5431. Min Act: -0.1700

Data Index: 4887153 (Open Web Text)

Max Activating Token Index: 744

Text #18

Max Range: 3.9867. Min Range: -3.9867

Max Act: 3.5286. Min Act: -0.1700

Data Index: 4593614 (Open Web Text)

Max Activating Token Index: 188

Text #19

Max Range: 3.9867. Min Range: -3.9867

Max Act: 3.5577. Min Act: -0.1700

Data Index: 4847905 (Open Web Text)

Max Activating Token Index: 379