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

Dataset: Open Web Text

Neuron 118 in Layer 6

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: 3.8727. Min Range: -3.8727

Max Act: 3.8727. Min Act: -0.1700

Data Index: 2060440 (Open Web Text)

Max Activating Token Index: 461

Text #1

Max Range: 3.8727. Min Range: -3.8727

Max Act: 3.8596. Min Act: -0.1700

Data Index: 5014703 (Open Web Text)

Max Activating Token Index: 994

Text #2

Max Range: 3.8727. Min Range: -3.8727

Max Act: 3.8505. Min Act: -0.1700

Data Index: 1572051 (Open Web Text)

Max Activating Token Index: 223

Text #3

Max Range: 3.8727. Min Range: -3.8727

Max Act: 3.8307. Min Act: -0.1700

Data Index: 288730 (Open Web Text)

Max Activating Token Index: 373

Text #4

Max Range: 3.8727. Min Range: -3.8727

Max Act: 3.8229. Min Act: -0.1700

Data Index: 5643509 (Open Web Text)

Max Activating Token Index: 745

Text #5

Max Range: 3.8727. Min Range: -3.8727

Max Act: 3.7892. Min Act: -0.1700

Data Index: 5626713 (Open Web Text)

Max Activating Token Index: 572

Text #6

Max Range: 3.8727. Min Range: -3.8727

Max Act: 3.7914. Min Act: -0.1700

Data Index: 8298320 (Open Web Text)

Max Activating Token Index: 698

Text #7

Max Range: 3.8727. Min Range: -3.8727

Max Act: 3.7552. Min Act: -0.1700

Data Index: 40766 (Open Web Text)

Max Activating Token Index: 992

Text #8

Max Range: 3.8727. Min Range: -3.8727

Max Act: 3.7640. Min Act: -0.1700

Data Index: 1543424 (Open Web Text)

Max Activating Token Index: 609

Text #9

Max Range: 3.8727. Min Range: -3.8727

Max Act: 3.7724. Min Act: -0.1700

Data Index: 2358017 (Open Web Text)

Max Activating Token Index: 193

Text #10

Max Range: 3.8727. Min Range: -3.8727

Max Act: 3.7404. Min Act: -0.1700

Data Index: 4457051 (Open Web Text)

Max Activating Token Index: 444

Text #11

Max Range: 3.8727. Min Range: -3.8727

Max Act: 3.6975. Min Act: -0.1700

Data Index: 1564900 (Open Web Text)

Max Activating Token Index: 356

Text #12

Max Range: 3.8727. Min Range: -3.8727

Max Act: 3.7151. Min Act: -0.1700

Data Index: 8663766 (Open Web Text)

Max Activating Token Index: 576

Text #13

Max Range: 3.8727. Min Range: -3.8727

Max Act: 3.7120. Min Act: -0.1700

Data Index: 205190 (Open Web Text)

Max Activating Token Index: 650

Text #14

Max Range: 3.8727. Min Range: -3.8727

Max Act: 3.6914. Min Act: -0.1700

Data Index: 1196762 (Open Web Text)

Max Activating Token Index: 747

Text #15

Max Range: 3.8727. Min Range: -3.8727

Max Act: 3.6762. Min Act: -0.1700

Data Index: 5144751 (Open Web Text)

Max Activating Token Index: 568

Text #16

Max Range: 3.8727. Min Range: -3.8727

Max Act: 3.6946. Min Act: -0.1700

Data Index: 5593739 (Open Web Text)

Max Activating Token Index: 857

Text #17

Max Range: 3.8727. Min Range: -3.8727

Max Act: 3.6760. Min Act: -0.1700

Data Index: 2130768 (Open Web Text)

Max Activating Token Index: 1012

Text #18

Max Range: 3.8727. Min Range: -3.8727

Max Act: 3.6586. Min Act: -0.1700

Data Index: 3169199 (Open Web Text)

Max Activating Token Index: 729

Text #19

Max Range: 3.8727. Min Range: -3.8727

Max Act: 3.6643. Min Act: -0.1700

Data Index: 657320 (Open Web Text)

Max Activating Token Index: 607