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

Dataset: Open Web Text

Neuron 1457 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: 4.1168. Min Range: -4.1168

Max Act: 4.1062. Min Act: -0.1700

Data Index: 3757812 (Open Web Text)

Max Activating Token Index: 971

Text #1

Max Range: 4.1168. Min Range: -4.1168

Max Act: 4.1168. Min Act: -0.1700

Data Index: 412721 (Open Web Text)

Max Activating Token Index: 605

Text #2

Max Range: 4.1168. Min Range: -4.1168

Max Act: 4.0894. Min Act: -0.1700

Data Index: 5989324 (Open Web Text)

Max Activating Token Index: 447

Text #3

Max Range: 4.1168. Min Range: -4.1168

Max Act: 4.0853. Min Act: -0.1700

Data Index: 6838273 (Open Web Text)

Max Activating Token Index: 178

Text #4

Max Range: 4.1168. Min Range: -4.1168

Max Act: 4.0749. Min Act: -0.1700

Data Index: 3816703 (Open Web Text)

Max Activating Token Index: 332

Text #5

Max Range: 4.1168. Min Range: -4.1168

Max Act: 4.0983. Min Act: -0.1700

Data Index: 2525818 (Open Web Text)

Max Activating Token Index: 511

Text #6

Max Range: 4.1168. Min Range: -4.1168

Max Act: 4.0709. Min Act: -0.1700

Data Index: 4486663 (Open Web Text)

Max Activating Token Index: 73

Text #7

Max Range: 4.1168. Min Range: -4.1168

Max Act: 4.0472. Min Act: -0.1700

Data Index: 2734634 (Open Web Text)

Max Activating Token Index: 551

Text #8

Max Range: 4.1168. Min Range: -4.1168

Max Act: 4.0621. Min Act: -0.1700

Data Index: 892209 (Open Web Text)

Max Activating Token Index: 318

Text #9

Max Range: 4.1168. Min Range: -4.1168

Max Act: 4.0633. Min Act: -0.1700

Data Index: 5578193 (Open Web Text)

Max Activating Token Index: 465

Text #10

Max Range: 4.1168. Min Range: -4.1168

Max Act: 4.0693. Min Act: -0.1700

Data Index: 476893 (Open Web Text)

Max Activating Token Index: 31

Text #11

Max Range: 4.1168. Min Range: -4.1168

Max Act: 4.0623. Min Act: -0.1700

Data Index: 5048851 (Open Web Text)

Max Activating Token Index: 199

Text #12

Max Range: 4.1168. Min Range: -4.1168

Max Act: 4.0488. Min Act: -0.1700

Data Index: 443536 (Open Web Text)

Max Activating Token Index: 9

Text #13

Max Range: 4.1168. Min Range: -4.1168

Max Act: 4.0364. Min Act: -0.1700

Data Index: 2083896 (Open Web Text)

Max Activating Token Index: 949

Text #14

Max Range: 4.1168. Min Range: -4.1168

Max Act: 4.0662. Min Act: -0.1700

Data Index: 4214826 (Open Web Text)

Max Activating Token Index: 72

Text #15

Max Range: 4.1168. Min Range: -4.1168

Max Act: 4.0549. Min Act: -0.1700

Data Index: 1923024 (Open Web Text)

Max Activating Token Index: 48

Text #16

Max Range: 4.1168. Min Range: -4.1168

Max Act: 4.0590. Min Act: -0.1700

Data Index: 3983590 (Open Web Text)

Max Activating Token Index: 115

Text #17

Max Range: 4.1168. Min Range: -4.1168

Max Act: 4.0631. Min Act: -0.1700

Data Index: 1670281 (Open Web Text)

Max Activating Token Index: 47

Text #18

Max Range: 4.1168. Min Range: -4.1168

Max Act: 4.0685. Min Act: -0.1700

Data Index: 3771669 (Open Web Text)

Max Activating Token Index: 223

Text #19

Max Range: 4.1168. Min Range: -4.1168

Max Act: 4.0393. Min Act: -0.1700

Data Index: 1661772 (Open Web Text)

Max Activating Token Index: 342