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

Dataset: Open Web Text

Neuron 1529 in Layer 1

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: 1.8811. Min Range: -1.8811

Max Act: 1.8811. Min Act: -0.1700

Data Index: 3526037 (Open Web Text)

Max Activating Token Index: 672

Text #1

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.8762. Min Act: -0.1700

Data Index: 4397739 (Open Web Text)

Max Activating Token Index: 74

Text #2

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.8671. Min Act: -0.1700

Data Index: 268693 (Open Web Text)

Max Activating Token Index: 277

Text #3

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.8635. Min Act: -0.1700

Data Index: 2277395 (Open Web Text)

Max Activating Token Index: 948

Text #4

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.8448. Min Act: -0.1700

Data Index: 847108 (Open Web Text)

Max Activating Token Index: 328

Text #5

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.8370. Min Act: -0.1700

Data Index: 6306681 (Open Web Text)

Max Activating Token Index: 631

Text #6

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.7996. Min Act: -0.1700

Data Index: 6223170 (Open Web Text)

Max Activating Token Index: 1001

Text #7

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.8105. Min Act: -0.1700

Data Index: 3582343 (Open Web Text)

Max Activating Token Index: 685

Text #8

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.8187. Min Act: -0.1700

Data Index: 4565123 (Open Web Text)

Max Activating Token Index: 531

Text #9

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.7980. Min Act: -0.1700

Data Index: 6915303 (Open Web Text)

Max Activating Token Index: 582

Text #10

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.7906. Min Act: -0.1700

Data Index: 286033 (Open Web Text)

Max Activating Token Index: 95

Text #11

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.7918. Min Act: -0.1700

Data Index: 4676952 (Open Web Text)

Max Activating Token Index: 858

Text #12

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.8013. Min Act: -0.1700

Data Index: 1743726 (Open Web Text)

Max Activating Token Index: 512

Text #13

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.8036. Min Act: -0.1700

Data Index: 7329099 (Open Web Text)

Max Activating Token Index: 605

Text #14

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.8006. Min Act: -0.1700

Data Index: 6895557 (Open Web Text)

Max Activating Token Index: 129

Text #15

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.7770. Min Act: -0.1700

Data Index: 1376851 (Open Web Text)

Max Activating Token Index: 309

Text #16

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.7803. Min Act: -0.1700

Data Index: 4308773 (Open Web Text)

Max Activating Token Index: 597

Text #17

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.7803. Min Act: -0.1700

Data Index: 6662592 (Open Web Text)

Max Activating Token Index: 1016

Text #18

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.7870. Min Act: -0.1700

Data Index: 285889 (Open Web Text)

Max Activating Token Index: 546

Text #19

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.7713. Min Act: -0.1700

Data Index: 721898 (Open Web Text)

Max Activating Token Index: 416