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

Dataset: Open Web Text

Neuron 728 in Layer 4

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: 3.3882. Min Range: -3.3882

Max Act: 3.3882. Min Act: -0.1700

Data Index: 2046915 (Open Web Text)

Max Activating Token Index: 263

Text #1

Max Range: 3.3882. Min Range: -3.3882

Max Act: 3.2716. Min Act: -0.1700

Data Index: 3471436 (Open Web Text)

Max Activating Token Index: 711

Text #2

Max Range: 3.3882. Min Range: -3.3882

Max Act: 3.2555. Min Act: -0.1700

Data Index: 4522901 (Open Web Text)

Max Activating Token Index: 826

Text #3

Max Range: 3.3882. Min Range: -3.3882

Max Act: 3.2209. Min Act: -0.1700

Data Index: 7130434 (Open Web Text)

Max Activating Token Index: 523

Text #4

Max Range: 3.3882. Min Range: -3.3882

Max Act: 3.2607. Min Act: -0.1700

Data Index: 7108423 (Open Web Text)

Max Activating Token Index: 915

Text #5

Max Range: 3.3882. Min Range: -3.3882

Max Act: 3.2281. Min Act: -0.1700

Data Index: 723716 (Open Web Text)

Max Activating Token Index: 566

Text #6

Max Range: 3.3882. Min Range: -3.3882

Max Act: 3.2069. Min Act: -0.1700

Data Index: 101803 (Open Web Text)

Max Activating Token Index: 523

Text #7

Max Range: 3.3882. Min Range: -3.3882

Max Act: 3.2054. Min Act: -0.1700

Data Index: 1759221 (Open Web Text)

Max Activating Token Index: 979

Text #8

Max Range: 3.3882. Min Range: -3.3882

Max Act: 3.2188. Min Act: -0.1700

Data Index: 1128072 (Open Web Text)

Max Activating Token Index: 945

Text #9

Max Range: 3.3882. Min Range: -3.3882

Max Act: 3.1910. Min Act: -0.1700

Data Index: 4684501 (Open Web Text)

Max Activating Token Index: 470

Text #10

Max Range: 3.3882. Min Range: -3.3882

Max Act: 3.1731. Min Act: -0.1700

Data Index: 4831075 (Open Web Text)

Max Activating Token Index: 242

Text #11

Max Range: 3.3882. Min Range: -3.3882

Max Act: 3.1860. Min Act: -0.1700

Data Index: 58087 (Open Web Text)

Max Activating Token Index: 596

Text #12

Max Range: 3.3882. Min Range: -3.3882

Max Act: 3.1921. Min Act: -0.1700

Data Index: 5746466 (Open Web Text)

Max Activating Token Index: 466

Text #13

Max Range: 3.3882. Min Range: -3.3882

Max Act: 3.1786. Min Act: -0.1700

Data Index: 4850209 (Open Web Text)

Max Activating Token Index: 617

Text #14

Max Range: 3.3882. Min Range: -3.3882

Max Act: 3.1670. Min Act: -0.1700

Data Index: 7542087 (Open Web Text)

Max Activating Token Index: 275

Text #15

Max Range: 3.3882. Min Range: -3.3882

Max Act: 3.1655. Min Act: -0.1700

Data Index: 5241769 (Open Web Text)

Max Activating Token Index: 692

Text #16

Max Range: 3.3882. Min Range: -3.3882

Max Act: 3.1669. Min Act: -0.1700

Data Index: 4126288 (Open Web Text)

Max Activating Token Index: 266

Text #17

Max Range: 3.3882. Min Range: -3.3882

Max Act: 3.1588. Min Act: -0.1700

Data Index: 1093820 (Open Web Text)

Max Activating Token Index: 961

Text #18

Max Range: 3.3882. Min Range: -3.3882

Max Act: 3.1659. Min Act: -0.1700

Data Index: 4867778 (Open Web Text)

Max Activating Token Index: 297

Text #19

Max Range: 3.3882. Min Range: -3.3882

Max Act: 3.1484. Min Act: -0.1700

Data Index: 6557077 (Open Web Text)

Max Activating Token Index: 398