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

Dataset: Open Web Text

Neuron 2349 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: 4.0375. Min Range: -4.0375

Max Act: 4.0375. Min Act: -0.1700

Data Index: 1450266 (Open Web Text)

Max Activating Token Index: 11

Text #1

Max Range: 4.0375. Min Range: -4.0375

Max Act: 3.8552. Min Act: -0.1700

Data Index: 3217529 (Open Web Text)

Max Activating Token Index: 138

Text #2

Max Range: 4.0375. Min Range: -4.0375

Max Act: 3.8205. Min Act: -0.1700

Data Index: 8014797 (Open Web Text)

Max Activating Token Index: 430

Text #3

Max Range: 4.0375. Min Range: -4.0375

Max Act: 3.7984. Min Act: -0.1700

Data Index: 7754876 (Open Web Text)

Max Activating Token Index: 710

Text #4

Max Range: 4.0375. Min Range: -4.0375

Max Act: 3.8118. Min Act: -0.1700

Data Index: 3741452 (Open Web Text)

Max Activating Token Index: 314

Text #5

Max Range: 4.0375. Min Range: -4.0375

Max Act: 3.8173. Min Act: -0.1700

Data Index: 4070552 (Open Web Text)

Max Activating Token Index: 426

Text #6

Max Range: 4.0375. Min Range: -4.0375

Max Act: 3.8101. Min Act: -0.1700

Data Index: 1407558 (Open Web Text)

Max Activating Token Index: 67

Text #7

Max Range: 4.0375. Min Range: -4.0375

Max Act: 3.8049. Min Act: -0.1700

Data Index: 4161193 (Open Web Text)

Max Activating Token Index: 216

Text #8

Max Range: 4.0375. Min Range: -4.0375

Max Act: 3.7817. Min Act: -0.1700

Data Index: 7098426 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 4.0375. Min Range: -4.0375

Max Act: 3.7647. Min Act: -0.1700

Data Index: 7697251 (Open Web Text)

Max Activating Token Index: 791

Text #10

Max Range: 4.0375. Min Range: -4.0375

Max Act: 3.7959. Min Act: -0.1700

Data Index: 5837358 (Open Web Text)

Max Activating Token Index: 757

Text #11

Max Range: 4.0375. Min Range: -4.0375

Max Act: 3.7833. Min Act: -0.1700

Data Index: 7160144 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 4.0375. Min Range: -4.0375

Max Act: 3.7760. Min Act: -0.1700

Data Index: 1773398 (Open Web Text)

Max Activating Token Index: 80

Text #13

Max Range: 4.0375. Min Range: -4.0375

Max Act: 3.7923. Min Act: -0.1700

Data Index: 6744787 (Open Web Text)

Max Activating Token Index: 485

Text #14

Max Range: 4.0375. Min Range: -4.0375

Max Act: 3.7341. Min Act: -0.1700

Data Index: 7367436 (Open Web Text)

Max Activating Token Index: 396

Text #15

Max Range: 4.0375. Min Range: -4.0375

Max Act: 3.7351. Min Act: -0.1700

Data Index: 3019496 (Open Web Text)

Max Activating Token Index: 635

Text #16

Max Range: 4.0375. Min Range: -4.0375

Max Act: 3.7358. Min Act: -0.1700

Data Index: 3487852 (Open Web Text)

Max Activating Token Index: 584

Text #17

Max Range: 4.0375. Min Range: -4.0375

Max Act: 3.7338. Min Act: -0.1700

Data Index: 6545478 (Open Web Text)

Max Activating Token Index: 240

Text #18

Max Range: 4.0375. Min Range: -4.0375

Max Act: 3.7447. Min Act: -0.1700

Data Index: 1925099 (Open Web Text)

Max Activating Token Index: 909

Text #19

Max Range: 4.0375. Min Range: -4.0375

Max Act: 3.7346. Min Act: -0.1700

Data Index: 1271438 (Open Web Text)

Max Activating Token Index: 13