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

Dataset: Open Web Text

Neuron 426 in Layer 4

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: 3.6028. Min Range: -3.6028

Max Act: 3.6028. Min Act: -0.1700

Data Index: 2327716 (Open Web Text)

Max Activating Token Index: 762

Text #1

Max Range: 3.6028. Min Range: -3.6028

Max Act: 3.5844. Min Act: -0.1700

Data Index: 2758663 (Open Web Text)

Max Activating Token Index: 816

Text #2

Max Range: 3.6028. Min Range: -3.6028

Max Act: 3.5284. Min Act: -0.1700

Data Index: 919186 (Open Web Text)

Max Activating Token Index: 800

Text #3

Max Range: 3.6028. Min Range: -3.6028

Max Act: 3.5230. Min Act: -0.1700

Data Index: 1079458 (Open Web Text)

Max Activating Token Index: 587

Text #4

Max Range: 3.6028. Min Range: -3.6028

Max Act: 3.5017. Min Act: -0.1700

Data Index: 3488233 (Open Web Text)

Max Activating Token Index: 753

Text #5

Max Range: 3.6028. Min Range: -3.6028

Max Act: 3.5170. Min Act: -0.1700

Data Index: 2944006 (Open Web Text)

Max Activating Token Index: 128

Text #6

Max Range: 3.6028. Min Range: -3.6028

Max Act: 3.4882. Min Act: -0.1700

Data Index: 6701075 (Open Web Text)

Max Activating Token Index: 1016

Text #7

Max Range: 3.6028. Min Range: -3.6028

Max Act: 3.4321. Min Act: -0.1700

Data Index: 6748135 (Open Web Text)

Max Activating Token Index: 26

Text #8

Max Range: 3.6028. Min Range: -3.6028

Max Act: 3.4541. Min Act: -0.1700

Data Index: 3675912 (Open Web Text)

Max Activating Token Index: 600

Text #9

Max Range: 3.6028. Min Range: -3.6028

Max Act: 3.4606. Min Act: -0.1700

Data Index: 7254611 (Open Web Text)

Max Activating Token Index: 138

Text #10

Max Range: 3.6028. Min Range: -3.6028

Max Act: 3.4569. Min Act: -0.1700

Data Index: 7298582 (Open Web Text)

Max Activating Token Index: 52

Text #11

Max Range: 3.6028. Min Range: -3.6028

Max Act: 3.4647. Min Act: -0.1700

Data Index: 1031769 (Open Web Text)

Max Activating Token Index: 588

Text #12

Max Range: 3.6028. Min Range: -3.6028

Max Act: 3.3934. Min Act: -0.1700

Data Index: 1416714 (Open Web Text)

Max Activating Token Index: 39

Text #13

Max Range: 3.6028. Min Range: -3.6028

Max Act: 3.4056. Min Act: -0.1700

Data Index: 7506817 (Open Web Text)

Max Activating Token Index: 619

Text #14

Max Range: 3.6028. Min Range: -3.6028

Max Act: 3.4162. Min Act: -0.1700

Data Index: 6947591 (Open Web Text)

Max Activating Token Index: 455

Text #15

Max Range: 3.6028. Min Range: -3.6028

Max Act: 3.3993. Min Act: -0.1700

Data Index: 3074906 (Open Web Text)

Max Activating Token Index: 512

Text #16

Max Range: 3.6028. Min Range: -3.6028

Max Act: 3.4049. Min Act: -0.1700

Data Index: 7198769 (Open Web Text)

Max Activating Token Index: 989

Text #17

Max Range: 3.6028. Min Range: -3.6028

Max Act: 3.3827. Min Act: -0.1700

Data Index: 5321971 (Open Web Text)

Max Activating Token Index: 269

Text #18

Max Range: 3.6028. Min Range: -3.6028

Max Act: 3.3521. Min Act: -0.1700

Data Index: 2958572 (Open Web Text)

Max Activating Token Index: 986

Text #19

Max Range: 3.6028. Min Range: -3.6028

Max Act: 3.3703. Min Act: -0.1700

Data Index: 776521 (Open Web Text)

Max Activating Token Index: 334