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

Dataset: Open Web Text

Neuron 488 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: 3.0990. Min Range: -3.0990

Max Act: 3.0990. Min Act: -0.1700

Data Index: 204187 (Open Web Text)

Max Activating Token Index: 1007

Text #1

Max Range: 3.0990. Min Range: -3.0990

Max Act: 3.0917. Min Act: -0.1700

Data Index: 2562421 (Open Web Text)

Max Activating Token Index: 312

Text #2

Max Range: 3.0990. Min Range: -3.0990

Max Act: 3.0817. Min Act: -0.1700

Data Index: 3740118 (Open Web Text)

Max Activating Token Index: 731

Text #3

Max Range: 3.0990. Min Range: -3.0990

Max Act: 3.0832. Min Act: -0.1700

Data Index: 2751140 (Open Web Text)

Max Activating Token Index: 697

Text #4

Max Range: 3.0990. Min Range: -3.0990

Max Act: 3.0642. Min Act: -0.1700

Data Index: 5638106 (Open Web Text)

Max Activating Token Index: 238

Text #5

Max Range: 3.0990. Min Range: -3.0990

Max Act: 3.0157. Min Act: -0.1700

Data Index: 3961686 (Open Web Text)

Max Activating Token Index: 1022

Text #6

Max Range: 3.0990. Min Range: -3.0990

Max Act: 3.0354. Min Act: -0.1700

Data Index: 7053725 (Open Web Text)

Max Activating Token Index: 30

Text #7

Max Range: 3.0990. Min Range: -3.0990

Max Act: 3.0137. Min Act: -0.1700

Data Index: 2842668 (Open Web Text)

Max Activating Token Index: 734

Text #8

Max Range: 3.0990. Min Range: -3.0990

Max Act: 2.9731. Min Act: -0.1700

Data Index: 4781507 (Open Web Text)

Max Activating Token Index: 587

Text #9

Max Range: 3.0990. Min Range: -3.0990

Max Act: 3.0200. Min Act: -0.1700

Data Index: 5731023 (Open Web Text)

Max Activating Token Index: 670

Text #10

Max Range: 3.0990. Min Range: -3.0990

Max Act: 3.0074. Min Act: -0.1700

Data Index: 5594353 (Open Web Text)

Max Activating Token Index: 545

Text #11

Max Range: 3.0990. Min Range: -3.0990

Max Act: 2.9691. Min Act: -0.1700

Data Index: 8196335 (Open Web Text)

Max Activating Token Index: 129

Text #12

Max Range: 3.0990. Min Range: -3.0990

Max Act: 2.9940. Min Act: -0.1700

Data Index: 2034428 (Open Web Text)

Max Activating Token Index: 690

Text #13

Max Range: 3.0990. Min Range: -3.0990

Max Act: 2.9901. Min Act: -0.1700

Data Index: 5496371 (Open Web Text)

Max Activating Token Index: 97

Text #14

Max Range: 3.0990. Min Range: -3.0990

Max Act: 2.9846. Min Act: -0.1700

Data Index: 1848865 (Open Web Text)

Max Activating Token Index: 180

Text #15

Max Range: 3.0990. Min Range: -3.0990

Max Act: 2.9625. Min Act: -0.1700

Data Index: 6539621 (Open Web Text)

Max Activating Token Index: 376

Text #16

Max Range: 3.0990. Min Range: -3.0990

Max Act: 2.9350. Min Act: -0.1700

Data Index: 3566032 (Open Web Text)

Max Activating Token Index: 141

Text #17

Max Range: 3.0990. Min Range: -3.0990

Max Act: 2.9482. Min Act: -0.1700

Data Index: 1953172 (Open Web Text)

Max Activating Token Index: 70

Text #18

Max Range: 3.0990. Min Range: -3.0990

Max Act: 2.9581. Min Act: -0.1700

Data Index: 496962 (Open Web Text)

Max Activating Token Index: 246

Text #19

Max Range: 3.0990. Min Range: -3.0990

Max Act: 2.9885. Min Act: -0.1700

Data Index: 7308959 (Open Web Text)

Max Activating Token Index: 817