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

Dataset: Open Web Text

Neuron 2018 in Layer 6

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: 3.7789. Min Range: -3.7789

Max Act: 3.7789. Min Act: -0.1700

Data Index: 7205609 (Open Web Text)

Max Activating Token Index: 488

Text #1

Max Range: 3.7789. Min Range: -3.7789

Max Act: 3.6818. Min Act: -0.1700

Data Index: 4923981 (Open Web Text)

Max Activating Token Index: 330

Text #2

Max Range: 3.7789. Min Range: -3.7789

Max Act: 3.7136. Min Act: -0.1700

Data Index: 252334 (Open Web Text)

Max Activating Token Index: 437

Text #3

Max Range: 3.7789. Min Range: -3.7789

Max Act: 3.6411. Min Act: -0.1700

Data Index: 1708634 (Open Web Text)

Max Activating Token Index: 857

Text #4

Max Range: 3.7789. Min Range: -3.7789

Max Act: 3.6264. Min Act: -0.1700

Data Index: 7155363 (Open Web Text)

Max Activating Token Index: 378

Text #5

Max Range: 3.7789. Min Range: -3.7789

Max Act: 3.6536. Min Act: -0.1700

Data Index: 5406838 (Open Web Text)

Max Activating Token Index: 406

Text #6

Max Range: 3.7789. Min Range: -3.7789

Max Act: 3.6805. Min Act: -0.1700

Data Index: 5590113 (Open Web Text)

Max Activating Token Index: 365

Text #7

Max Range: 3.7789. Min Range: -3.7789

Max Act: 3.6877. Min Act: -0.1700

Data Index: 4184185 (Open Web Text)

Max Activating Token Index: 322

Text #8

Max Range: 3.7789. Min Range: -3.7789

Max Act: 3.6386. Min Act: -0.1700

Data Index: 3871554 (Open Web Text)

Max Activating Token Index: 483

Text #9

Max Range: 3.7789. Min Range: -3.7789

Max Act: 3.6395. Min Act: -0.1700

Data Index: 81154 (Open Web Text)

Max Activating Token Index: 432

Text #10

Max Range: 3.7789. Min Range: -3.7789

Max Act: 3.6441. Min Act: -0.1700

Data Index: 1868202 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 3.7789. Min Range: -3.7789

Max Act: 3.6416. Min Act: -0.1700

Data Index: 2996274 (Open Web Text)

Max Activating Token Index: 69

Text #12

Max Range: 3.7789. Min Range: -3.7789

Max Act: 3.6453. Min Act: -0.1700

Data Index: 405246 (Open Web Text)

Max Activating Token Index: 548

Text #13

Max Range: 3.7789. Min Range: -3.7789

Max Act: 3.6736. Min Act: -0.1700

Data Index: 8355432 (Open Web Text)

Max Activating Token Index: 953

Text #14

Max Range: 3.7789. Min Range: -3.7789

Max Act: 3.6441. Min Act: -0.1700

Data Index: 6585048 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 3.7789. Min Range: -3.7789

Max Act: 3.6419. Min Act: -0.1700

Data Index: 2642354 (Open Web Text)

Max Activating Token Index: 21

Text #16

Max Range: 3.7789. Min Range: -3.7789

Max Act: 3.5950. Min Act: -0.1700

Data Index: 229377 (Open Web Text)

Max Activating Token Index: 415

Text #17

Max Range: 3.7789. Min Range: -3.7789

Max Act: 3.6084. Min Act: -0.1700

Data Index: 1385568 (Open Web Text)

Max Activating Token Index: 311

Text #18

Max Range: 3.7789. Min Range: -3.7789

Max Act: 3.6651. Min Act: -0.1700

Data Index: 4174459 (Open Web Text)

Max Activating Token Index: 500

Text #19

Max Range: 3.7789. Min Range: -3.7789

Max Act: 3.5890. Min Act: -0.1700

Data Index: 1956339 (Open Web Text)

Max Activating Token Index: 615