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

Dataset: Open Web Text

Neuron 657 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: 3.0873. Min Range: -3.0873

Max Act: 3.0873. Min Act: -0.1700

Data Index: 7068335 (Open Web Text)

Max Activating Token Index: 495

Text #1

Max Range: 3.0873. Min Range: -3.0873

Max Act: 3.0715. Min Act: -0.1700

Data Index: 4744841 (Open Web Text)

Max Activating Token Index: 452

Text #2

Max Range: 3.0873. Min Range: -3.0873

Max Act: 3.0374. Min Act: -0.1700

Data Index: 5480532 (Open Web Text)

Max Activating Token Index: 338

Text #3

Max Range: 3.0873. Min Range: -3.0873

Max Act: 3.0422. Min Act: -0.1700

Data Index: 7081397 (Open Web Text)

Max Activating Token Index: 496

Text #4

Max Range: 3.0873. Min Range: -3.0873

Max Act: 2.9987. Min Act: -0.1700

Data Index: 403229 (Open Web Text)

Max Activating Token Index: 538

Text #5

Max Range: 3.0873. Min Range: -3.0873

Max Act: 2.9986. Min Act: -0.1700

Data Index: 5123988 (Open Web Text)

Max Activating Token Index: 223

Text #6

Max Range: 3.0873. Min Range: -3.0873

Max Act: 2.9812. Min Act: -0.1700

Data Index: 4076979 (Open Web Text)

Max Activating Token Index: 391

Text #7

Max Range: 3.0873. Min Range: -3.0873

Max Act: 2.9696. Min Act: -0.1700

Data Index: 5598567 (Open Web Text)

Max Activating Token Index: 321

Text #8

Max Range: 3.0873. Min Range: -3.0873

Max Act: 2.9773. Min Act: -0.1700

Data Index: 93749 (Open Web Text)

Max Activating Token Index: 455

Text #9

Max Range: 3.0873. Min Range: -3.0873

Max Act: 2.9717. Min Act: -0.1700

Data Index: 7488611 (Open Web Text)

Max Activating Token Index: 896

Text #10

Max Range: 3.0873. Min Range: -3.0873

Max Act: 2.9482. Min Act: -0.1700

Data Index: 7081297 (Open Web Text)

Max Activating Token Index: 302

Text #11

Max Range: 3.0873. Min Range: -3.0873

Max Act: 2.9577. Min Act: -0.1700

Data Index: 4462865 (Open Web Text)

Max Activating Token Index: 420

Text #12

Max Range: 3.0873. Min Range: -3.0873

Max Act: 2.9315. Min Act: -0.1700

Data Index: 6737830 (Open Web Text)

Max Activating Token Index: 604

Text #13

Max Range: 3.0873. Min Range: -3.0873

Max Act: 2.9539. Min Act: -0.1700

Data Index: 1565730 (Open Web Text)

Max Activating Token Index: 484

Text #14

Max Range: 3.0873. Min Range: -3.0873

Max Act: 2.9359. Min Act: -0.1700

Data Index: 3913596 (Open Web Text)

Max Activating Token Index: 114

Text #15

Max Range: 3.0873. Min Range: -3.0873

Max Act: 2.9365. Min Act: -0.1700

Data Index: 2645469 (Open Web Text)

Max Activating Token Index: 217

Text #16

Max Range: 3.0873. Min Range: -3.0873

Max Act: 2.9384. Min Act: -0.1700

Data Index: 1821391 (Open Web Text)

Max Activating Token Index: 262

Text #17

Max Range: 3.0873. Min Range: -3.0873

Max Act: 2.9323. Min Act: -0.1700

Data Index: 6162730 (Open Web Text)

Max Activating Token Index: 79

Text #18

Max Range: 3.0873. Min Range: -3.0873

Max Act: 2.9367. Min Act: -0.1700

Data Index: 5357025 (Open Web Text)

Max Activating Token Index: 655

Text #19

Max Range: 3.0873. Min Range: -3.0873

Max Act: 2.9563. Min Act: -0.1700

Data Index: 5755475 (Open Web Text)

Max Activating Token Index: 351