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

Dataset: Open Web Text

Neuron 856 in Layer 5

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: 3.1681. Min Range: -3.1681

Max Act: 3.1681. Min Act: -0.1700

Data Index: 3943919 (Open Web Text)

Max Activating Token Index: 616

Text #1

Max Range: 3.1681. Min Range: -3.1681

Max Act: 3.0748. Min Act: -0.1700

Data Index: 8051153 (Open Web Text)

Max Activating Token Index: 499

Text #2

Max Range: 3.1681. Min Range: -3.1681

Max Act: 3.0485. Min Act: -0.1700

Data Index: 3621207 (Open Web Text)

Max Activating Token Index: 229

Text #3

Max Range: 3.1681. Min Range: -3.1681

Max Act: 3.0088. Min Act: -0.1700

Data Index: 2501636 (Open Web Text)

Max Activating Token Index: 361

Text #4

Max Range: 3.1681. Min Range: -3.1681

Max Act: 2.9587. Min Act: -0.1700

Data Index: 4097009 (Open Web Text)

Max Activating Token Index: 175

Text #5

Max Range: 3.1681. Min Range: -3.1681

Max Act: 2.9519. Min Act: -0.1700

Data Index: 1585611 (Open Web Text)

Max Activating Token Index: 469

Text #6

Max Range: 3.1681. Min Range: -3.1681

Max Act: 2.9008. Min Act: -0.1700

Data Index: 2418596 (Open Web Text)

Max Activating Token Index: 556

Text #7

Max Range: 3.1681. Min Range: -3.1681

Max Act: 2.9067. Min Act: -0.1700

Data Index: 2024966 (Open Web Text)

Max Activating Token Index: 854

Text #8

Max Range: 3.1681. Min Range: -3.1681

Max Act: 2.8936. Min Act: -0.1700

Data Index: 3845547 (Open Web Text)

Max Activating Token Index: 443

Text #9

Max Range: 3.1681. Min Range: -3.1681

Max Act: 2.8936. Min Act: -0.1700

Data Index: 7246225 (Open Web Text)

Max Activating Token Index: 217

Text #10

Max Range: 3.1681. Min Range: -3.1681

Max Act: 2.8956. Min Act: -0.1700

Data Index: 6709337 (Open Web Text)

Max Activating Token Index: 460

Text #11

Max Range: 3.1681. Min Range: -3.1681

Max Act: 2.8816. Min Act: -0.1700

Data Index: 5516423 (Open Web Text)

Max Activating Token Index: 253

Text #12

Max Range: 3.1681. Min Range: -3.1681

Max Act: 2.8767. Min Act: -0.1700

Data Index: 468714 (Open Web Text)

Max Activating Token Index: 598

Text #13

Max Range: 3.1681. Min Range: -3.1681

Max Act: 2.8479. Min Act: -0.1700

Data Index: 4485037 (Open Web Text)

Max Activating Token Index: 721

Text #14

Max Range: 3.1681. Min Range: -3.1681

Max Act: 2.8383. Min Act: -0.1700

Data Index: 7487796 (Open Web Text)

Max Activating Token Index: 48

Text #15

Max Range: 3.1681. Min Range: -3.1681

Max Act: 2.8364. Min Act: -0.1700

Data Index: 6278872 (Open Web Text)

Max Activating Token Index: 500

Text #16

Max Range: 3.1681. Min Range: -3.1681

Max Act: 2.8335. Min Act: -0.1700

Data Index: 1174522 (Open Web Text)

Max Activating Token Index: 741

Text #17

Max Range: 3.1681. Min Range: -3.1681

Max Act: 2.8106. Min Act: -0.1700

Data Index: 8199393 (Open Web Text)

Max Activating Token Index: 484

Text #18

Max Range: 3.1681. Min Range: -3.1681

Max Act: 2.7976. Min Act: -0.1700

Data Index: 5169806 (Open Web Text)

Max Activating Token Index: 440

Text #19

Max Range: 3.1681. Min Range: -3.1681

Max Act: 2.8055. Min Act: -0.1700

Data Index: 6160844 (Open Web Text)

Max Activating Token Index: 221