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

Dataset: Open Web Text

Neuron 2028 in Layer 2

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: 3.6617. Min Range: -3.6617

Max Act: 3.6617. Min Act: -0.1700

Data Index: 3895661 (Open Web Text)

Max Activating Token Index: 51

Text #1

Max Range: 3.6617. Min Range: -3.6617

Max Act: 3.5654. Min Act: -0.1700

Data Index: 404844 (Open Web Text)

Max Activating Token Index: 237

Text #2

Max Range: 3.6617. Min Range: -3.6617

Max Act: 3.5130. Min Act: -0.1700

Data Index: 7861565 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.6617. Min Range: -3.6617

Max Act: 3.5378. Min Act: -0.1700

Data Index: 5568023 (Open Web Text)

Max Activating Token Index: 418

Text #4

Max Range: 3.6617. Min Range: -3.6617

Max Act: 3.4889. Min Act: -0.1700

Data Index: 7176746 (Open Web Text)

Max Activating Token Index: 50

Text #5

Max Range: 3.6617. Min Range: -3.6617

Max Act: 3.4942. Min Act: -0.1700

Data Index: 5363129 (Open Web Text)

Max Activating Token Index: 151

Text #6

Max Range: 3.6617. Min Range: -3.6617

Max Act: 3.4564. Min Act: -0.1700

Data Index: 2246868 (Open Web Text)

Max Activating Token Index: 432

Text #7

Max Range: 3.6617. Min Range: -3.6617

Max Act: 3.4470. Min Act: -0.1700

Data Index: 470923 (Open Web Text)

Max Activating Token Index: 1006

Text #8

Max Range: 3.6617. Min Range: -3.6617

Max Act: 3.4622. Min Act: -0.1700

Data Index: 3828065 (Open Web Text)

Max Activating Token Index: 121

Text #9

Max Range: 3.6617. Min Range: -3.6617

Max Act: 3.4347. Min Act: -0.1700

Data Index: 2548049 (Open Web Text)

Max Activating Token Index: 779

Text #10

Max Range: 3.6617. Min Range: -3.6617

Max Act: 3.4348. Min Act: -0.1700

Data Index: 5643937 (Open Web Text)

Max Activating Token Index: 331

Text #11

Max Range: 3.6617. Min Range: -3.6617

Max Act: 3.4141. Min Act: -0.1700

Data Index: 7883054 (Open Web Text)

Max Activating Token Index: 168

Text #12

Max Range: 3.6617. Min Range: -3.6617

Max Act: 3.4084. Min Act: -0.1700

Data Index: 4435323 (Open Web Text)

Max Activating Token Index: 321

Text #13

Max Range: 3.6617. Min Range: -3.6617

Max Act: 3.4014. Min Act: -0.1700

Data Index: 3124386 (Open Web Text)

Max Activating Token Index: 268

Text #14

Max Range: 3.6617. Min Range: -3.6617

Max Act: 3.4128. Min Act: -0.1700

Data Index: 7556051 (Open Web Text)

Max Activating Token Index: 800

Text #15

Max Range: 3.6617. Min Range: -3.6617

Max Act: 3.3854. Min Act: -0.1700

Data Index: 6546754 (Open Web Text)

Max Activating Token Index: 258

Text #16

Max Range: 3.6617. Min Range: -3.6617

Max Act: 3.3877. Min Act: -0.1700

Data Index: 6286673 (Open Web Text)

Max Activating Token Index: 65

Text #17

Max Range: 3.6617. Min Range: -3.6617

Max Act: 3.3719. Min Act: -0.1700

Data Index: 5943861 (Open Web Text)

Max Activating Token Index: 940

Text #18

Max Range: 3.6617. Min Range: -3.6617

Max Act: 3.3770. Min Act: -0.1700

Data Index: 5821236 (Open Web Text)

Max Activating Token Index: 48

Text #19

Max Range: 3.6617. Min Range: -3.6617

Max Act: 3.3713. Min Act: -0.1700

Data Index: 2246869 (Open Web Text)

Max Activating Token Index: 315