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

Dataset: Open Web Text

Neuron 1688 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: 4.1736. Min Range: -4.1736

Max Act: 4.1736. Min Act: -0.1700

Data Index: 3724685 (Open Web Text)

Max Activating Token Index: 346

Text #1

Max Range: 4.1736. Min Range: -4.1736

Max Act: 4.0455. Min Act: -0.1700

Data Index: 6502051 (Open Web Text)

Max Activating Token Index: 144

Text #2

Max Range: 4.1736. Min Range: -4.1736

Max Act: 3.9585. Min Act: -0.1700

Data Index: 3387431 (Open Web Text)

Max Activating Token Index: 400

Text #3

Max Range: 4.1736. Min Range: -4.1736

Max Act: 3.9275. Min Act: -0.1700

Data Index: 7816476 (Open Web Text)

Max Activating Token Index: 479

Text #4

Max Range: 4.1736. Min Range: -4.1736

Max Act: 3.9323. Min Act: -0.1700

Data Index: 3569253 (Open Web Text)

Max Activating Token Index: 29

Text #5

Max Range: 4.1736. Min Range: -4.1736

Max Act: 3.9100. Min Act: -0.1700

Data Index: 1396582 (Open Web Text)

Max Activating Token Index: 97

Text #6

Max Range: 4.1736. Min Range: -4.1736

Max Act: 3.8714. Min Act: -0.1700

Data Index: 321718 (Open Web Text)

Max Activating Token Index: 66

Text #7

Max Range: 4.1736. Min Range: -4.1736

Max Act: 3.8650. Min Act: -0.1700

Data Index: 1834001 (Open Web Text)

Max Activating Token Index: 85

Text #8

Max Range: 4.1736. Min Range: -4.1736

Max Act: 3.8548. Min Act: -0.1700

Data Index: 5941472 (Open Web Text)

Max Activating Token Index: 799

Text #9

Max Range: 4.1736. Min Range: -4.1736

Max Act: 3.8295. Min Act: -0.1700

Data Index: 7454031 (Open Web Text)

Max Activating Token Index: 238

Text #10

Max Range: 4.1736. Min Range: -4.1736

Max Act: 3.8219. Min Act: -0.1700

Data Index: 3654456 (Open Web Text)

Max Activating Token Index: 461

Text #11

Max Range: 4.1736. Min Range: -4.1736

Max Act: 3.8093. Min Act: -0.1700

Data Index: 2048832 (Open Web Text)

Max Activating Token Index: 864

Text #12

Max Range: 4.1736. Min Range: -4.1736

Max Act: 3.8252. Min Act: -0.1700

Data Index: 2500470 (Open Web Text)

Max Activating Token Index: 95

Text #13

Max Range: 4.1736. Min Range: -4.1736

Max Act: 3.8046. Min Act: -0.1700

Data Index: 6830767 (Open Web Text)

Max Activating Token Index: 676

Text #14

Max Range: 4.1736. Min Range: -4.1736

Max Act: 3.8112. Min Act: -0.1700

Data Index: 1227281 (Open Web Text)

Max Activating Token Index: 148

Text #15

Max Range: 4.1736. Min Range: -4.1736

Max Act: 3.7838. Min Act: -0.1700

Data Index: 5902232 (Open Web Text)

Max Activating Token Index: 606

Text #16

Max Range: 4.1736. Min Range: -4.1736

Max Act: 3.7917. Min Act: -0.1700

Data Index: 7390773 (Open Web Text)

Max Activating Token Index: 675

Text #17

Max Range: 4.1736. Min Range: -4.1736

Max Act: 3.7794. Min Act: -0.1700

Data Index: 7278670 (Open Web Text)

Max Activating Token Index: 252

Text #18

Max Range: 4.1736. Min Range: -4.1736

Max Act: 3.7430. Min Act: -0.1700

Data Index: 801123 (Open Web Text)

Max Activating Token Index: 915

Text #19

Max Range: 4.1736. Min Range: -4.1736

Max Act: 3.7598. Min Act: -0.1700

Data Index: 290050 (Open Web Text)

Max Activating Token Index: 384