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

Dataset: Open Web Text

Neuron 1665 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: 3.7697. Min Range: -3.7697

Max Act: 3.7697. Min Act: -0.1700

Data Index: 2859938 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 3.7697. Min Range: -3.7697

Max Act: 3.6049. Min Act: -0.1700

Data Index: 8701722 (Open Web Text)

Max Activating Token Index: 12

Text #2

Max Range: 3.7697. Min Range: -3.7697

Max Act: 3.5690. Min Act: -0.1700

Data Index: 3139386 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 3.7697. Min Range: -3.7697

Max Act: 3.5579. Min Act: -0.1700

Data Index: 5870670 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 3.7697. Min Range: -3.7697

Max Act: 3.5733. Min Act: -0.1700

Data Index: 332594 (Open Web Text)

Max Activating Token Index: 8

Text #5

Max Range: 3.7697. Min Range: -3.7697

Max Act: 3.5582. Min Act: -0.1700

Data Index: 3523076 (Open Web Text)

Max Activating Token Index: 9

Text #6

Max Range: 3.7697. Min Range: -3.7697

Max Act: 3.5698. Min Act: -0.1700

Data Index: 5294780 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 3.7697. Min Range: -3.7697

Max Act: 3.5131. Min Act: -0.1700

Data Index: 5701167 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 3.7697. Min Range: -3.7697

Max Act: 3.4918. Min Act: -0.1700

Data Index: 7130778 (Open Web Text)

Max Activating Token Index: 315

Text #9

Max Range: 3.7697. Min Range: -3.7697

Max Act: 3.5043. Min Act: -0.1700

Data Index: 6369198 (Open Web Text)

Max Activating Token Index: 13

Text #10

Max Range: 3.7697. Min Range: -3.7697

Max Act: 3.4908. Min Act: -0.1700

Data Index: 3419985 (Open Web Text)

Max Activating Token Index: 329

Text #11

Max Range: 3.7697. Min Range: -3.7697

Max Act: 3.5224. Min Act: -0.1700

Data Index: 6114020 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 3.7697. Min Range: -3.7697

Max Act: 3.4921. Min Act: -0.1700

Data Index: 2187919 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 3.7697. Min Range: -3.7697

Max Act: 3.4968. Min Act: -0.1700

Data Index: 3000762 (Open Web Text)

Max Activating Token Index: 9

Text #14

Max Range: 3.7697. Min Range: -3.7697

Max Act: 3.4916. Min Act: -0.1700

Data Index: 3050949 (Open Web Text)

Max Activating Token Index: 305

Text #15

Max Range: 3.7697. Min Range: -3.7697

Max Act: 3.4871. Min Act: -0.1700

Data Index: 3246347 (Open Web Text)

Max Activating Token Index: 190

Text #16

Max Range: 3.7697. Min Range: -3.7697

Max Act: 3.4820. Min Act: -0.1700

Data Index: 5610074 (Open Web Text)

Max Activating Token Index: 365

Text #17

Max Range: 3.7697. Min Range: -3.7697

Max Act: 3.4859. Min Act: -0.1700

Data Index: 5551753 (Open Web Text)

Max Activating Token Index: 970

Text #18

Max Range: 3.7697. Min Range: -3.7697

Max Act: 3.4657. Min Act: -0.1700

Data Index: 562581 (Open Web Text)

Max Activating Token Index: 920

Text #19

Max Range: 3.7697. Min Range: -3.7697

Max Act: 3.4742. Min Act: -0.1700

Data Index: 2683470 (Open Web Text)

Max Activating Token Index: 5