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

Dataset: Open Web Text

Neuron 2496 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: 1.3392. Min Range: -1.3392

Max Act: 1.3392. Min Act: -0.1321

Data Index: 1307979 (Open Web Text)

Max Activating Token Index: 1011

Text #1

Max Range: 1.3392. Min Range: -1.3392

Max Act: 1.3287. Min Act: 0.0005

Data Index: 3283519 (Open Web Text)

Max Activating Token Index: 1006

Text #2

Max Range: 1.3392. Min Range: -1.3392

Max Act: 1.3149. Min Act: -0.0845

Data Index: 924576 (Open Web Text)

Max Activating Token Index: 991

Text #3

Max Range: 1.3392. Min Range: -1.3392

Max Act: 1.3037. Min Act: -0.0695

Data Index: 2543506 (Open Web Text)

Max Activating Token Index: 1012

Text #4

Max Range: 1.3392. Min Range: -1.3392

Max Act: 1.3034. Min Act: -0.0352

Data Index: 6545372 (Open Web Text)

Max Activating Token Index: 1013

Text #5

Max Range: 1.3392. Min Range: -1.3392

Max Act: 1.3010. Min Act: -0.1098

Data Index: 4258217 (Open Web Text)

Max Activating Token Index: 1006

Text #6

Max Range: 1.3392. Min Range: -1.3392

Max Act: 1.2872. Min Act: -0.0330

Data Index: 8240947 (Open Web Text)

Max Activating Token Index: 989

Text #7

Max Range: 1.3392. Min Range: -1.3392

Max Act: 1.2892. Min Act: -0.0571

Data Index: 8363878 (Open Web Text)

Max Activating Token Index: 1004

Text #8

Max Range: 1.3392. Min Range: -1.3392

Max Act: 1.2870. Min Act: -0.0287

Data Index: 2730185 (Open Web Text)

Max Activating Token Index: 968

Text #9

Max Range: 1.3392. Min Range: -1.3392

Max Act: 1.2913. Min Act: -0.0483

Data Index: 627759 (Open Web Text)

Max Activating Token Index: 1007

Text #10

Max Range: 1.3392. Min Range: -1.3392

Max Act: 1.2819. Min Act: 0.0011

Data Index: 3905385 (Open Web Text)

Max Activating Token Index: 1021

Text #11

Max Range: 1.3392. Min Range: -1.3392

Max Act: 1.2832. Min Act: -0.0424

Data Index: 3465322 (Open Web Text)

Max Activating Token Index: 986

Text #12

Max Range: 1.3392. Min Range: -1.3392

Max Act: 1.2792. Min Act: -0.0243

Data Index: 1470377 (Open Web Text)

Max Activating Token Index: 1006

Text #13

Max Range: 1.3392. Min Range: -1.3392

Max Act: 1.2807. Min Act: -0.0527

Data Index: 4953742 (Open Web Text)

Max Activating Token Index: 1012

Text #14

Max Range: 1.3392. Min Range: -1.3392

Max Act: 1.2844. Min Act: -0.0081

Data Index: 7785353 (Open Web Text)

Max Activating Token Index: 953

Text #15

Max Range: 1.3392. Min Range: -1.3392

Max Act: 1.2824. Min Act: -0.1472

Data Index: 3833891 (Open Web Text)

Max Activating Token Index: 1004

Text #16

Max Range: 1.3392. Min Range: -1.3392

Max Act: 1.2709. Min Act: -0.0763

Data Index: 2677540 (Open Web Text)

Max Activating Token Index: 1009

Text #17

Max Range: 1.3392. Min Range: -1.3392

Max Act: 1.2786. Min Act: -0.0637

Data Index: 953508 (Open Web Text)

Max Activating Token Index: 1005

Text #18

Max Range: 1.3392. Min Range: -1.3392

Max Act: 1.2742. Min Act: -0.0905

Data Index: 1667366 (Open Web Text)

Max Activating Token Index: 1020

Text #19

Max Range: 1.3392. Min Range: -1.3392

Max Act: 1.2663. Min Act: -0.0621

Data Index: 7371110 (Open Web Text)

Max Activating Token Index: 997