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

Dataset: Open Web Text

Neuron 1008 in Layer 3

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: 3.4841. Min Range: -3.4841

Max Act: 3.4797. Min Act: -0.1700

Data Index: 565185 (Open Web Text)

Max Activating Token Index: 793

Text #1

Max Range: 3.4841. Min Range: -3.4841

Max Act: 3.4841. Min Act: -0.1700

Data Index: 4517914 (Open Web Text)

Max Activating Token Index: 739

Text #2

Max Range: 3.4841. Min Range: -3.4841

Max Act: 3.4456. Min Act: -0.1700

Data Index: 3918000 (Open Web Text)

Max Activating Token Index: 20

Text #3

Max Range: 3.4841. Min Range: -3.4841

Max Act: 3.4294. Min Act: -0.1700

Data Index: 1148589 (Open Web Text)

Max Activating Token Index: 1009

Text #4

Max Range: 3.4841. Min Range: -3.4841

Max Act: 3.4607. Min Act: -0.1700

Data Index: 216170 (Open Web Text)

Max Activating Token Index: 530

Text #5

Max Range: 3.4841. Min Range: -3.4841

Max Act: 3.4092. Min Act: -0.1700

Data Index: 5594448 (Open Web Text)

Max Activating Token Index: 475

Text #6

Max Range: 3.4841. Min Range: -3.4841

Max Act: 3.4035. Min Act: -0.1700

Data Index: 1900731 (Open Web Text)

Max Activating Token Index: 618

Text #7

Max Range: 3.4841. Min Range: -3.4841

Max Act: 3.4115. Min Act: -0.1700

Data Index: 8090895 (Open Web Text)

Max Activating Token Index: 914

Text #8

Max Range: 3.4841. Min Range: -3.4841

Max Act: 3.4069. Min Act: -0.1700

Data Index: 2276758 (Open Web Text)

Max Activating Token Index: 77

Text #9

Max Range: 3.4841. Min Range: -3.4841

Max Act: 3.3828. Min Act: -0.1700

Data Index: 5731967 (Open Web Text)

Max Activating Token Index: 505

Text #10

Max Range: 3.4841. Min Range: -3.4841

Max Act: 3.3714. Min Act: -0.1700

Data Index: 3918004 (Open Web Text)

Max Activating Token Index: 75

Text #11

Max Range: 3.4841. Min Range: -3.4841

Max Act: 3.3543. Min Act: -0.1700

Data Index: 2910748 (Open Web Text)

Max Activating Token Index: 365

Text #12

Max Range: 3.4841. Min Range: -3.4841

Max Act: 3.3849. Min Act: -0.1700

Data Index: 7929417 (Open Web Text)

Max Activating Token Index: 486

Text #13

Max Range: 3.4841. Min Range: -3.4841

Max Act: 3.3678. Min Act: -0.1700

Data Index: 2579501 (Open Web Text)

Max Activating Token Index: 999

Text #14

Max Range: 3.4841. Min Range: -3.4841

Max Act: 3.3825. Min Act: -0.1700

Data Index: 5980990 (Open Web Text)

Max Activating Token Index: 463

Text #15

Max Range: 3.4841. Min Range: -3.4841

Max Act: 3.3609. Min Act: -0.1700

Data Index: 62382 (Open Web Text)

Max Activating Token Index: 200

Text #16

Max Range: 3.4841. Min Range: -3.4841

Max Act: 3.3772. Min Act: -0.1700

Data Index: 3918009 (Open Web Text)

Max Activating Token Index: 28

Text #17

Max Range: 3.4841. Min Range: -3.4841

Max Act: 3.3604. Min Act: -0.1700

Data Index: 4964281 (Open Web Text)

Max Activating Token Index: 907

Text #18

Max Range: 3.4841. Min Range: -3.4841

Max Act: 3.3795. Min Act: -0.1700

Data Index: 3917995 (Open Web Text)

Max Activating Token Index: 242

Text #19

Max Range: 3.4841. Min Range: -3.4841

Max Act: 3.3927. Min Act: -0.1700

Data Index: 4288461 (Open Web Text)

Max Activating Token Index: 395