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

Dataset: Open Web Text

Neuron 2895 in Layer 2

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: 2.0017. Min Range: -2.0017

Max Act: 2.0017. Min Act: -0.1700

Data Index: 2847898 (Open Web Text)

Max Activating Token Index: 661

Text #1

Max Range: 2.0017. Min Range: -2.0017

Max Act: 1.9949. Min Act: -0.1700

Data Index: 141973 (Open Web Text)

Max Activating Token Index: 471

Text #2

Max Range: 2.0017. Min Range: -2.0017

Max Act: 1.9532. Min Act: -0.1700

Data Index: 354684 (Open Web Text)

Max Activating Token Index: 956

Text #3

Max Range: 2.0017. Min Range: -2.0017

Max Act: 1.9487. Min Act: -0.1700

Data Index: 2976317 (Open Web Text)

Max Activating Token Index: 923

Text #4

Max Range: 2.0017. Min Range: -2.0017

Max Act: 1.9276. Min Act: -0.1700

Data Index: 1585533 (Open Web Text)

Max Activating Token Index: 472

Text #5

Max Range: 2.0017. Min Range: -2.0017

Max Act: 1.9061. Min Act: -0.1700

Data Index: 3981691 (Open Web Text)

Max Activating Token Index: 371

Text #6

Max Range: 2.0017. Min Range: -2.0017

Max Act: 1.8829. Min Act: -0.1700

Data Index: 8502003 (Open Web Text)

Max Activating Token Index: 807

Text #7

Max Range: 2.0017. Min Range: -2.0017

Max Act: 1.8932. Min Act: -0.1700

Data Index: 6111842 (Open Web Text)

Max Activating Token Index: 890

Text #8

Max Range: 2.0017. Min Range: -2.0017

Max Act: 1.8992. Min Act: -0.1700

Data Index: 4627354 (Open Web Text)

Max Activating Token Index: 359

Text #9

Max Range: 2.0017. Min Range: -2.0017

Max Act: 1.8436. Min Act: -0.1700

Data Index: 5594599 (Open Web Text)

Max Activating Token Index: 439

Text #10

Max Range: 2.0017. Min Range: -2.0017

Max Act: 1.8566. Min Act: -0.1700

Data Index: 4149564 (Open Web Text)

Max Activating Token Index: 391

Text #11

Max Range: 2.0017. Min Range: -2.0017

Max Act: 1.8339. Min Act: -0.1700

Data Index: 4117180 (Open Web Text)

Max Activating Token Index: 639

Text #12

Max Range: 2.0017. Min Range: -2.0017

Max Act: 1.8611. Min Act: -0.1700

Data Index: 2021272 (Open Web Text)

Max Activating Token Index: 373

Text #13

Max Range: 2.0017. Min Range: -2.0017

Max Act: 1.8504. Min Act: -0.1700

Data Index: 3163988 (Open Web Text)

Max Activating Token Index: 50

Text #14

Max Range: 2.0017. Min Range: -2.0017

Max Act: 1.8561. Min Act: -0.1700

Data Index: 4584892 (Open Web Text)

Max Activating Token Index: 537

Text #15

Max Range: 2.0017. Min Range: -2.0017

Max Act: 1.8241. Min Act: -0.1700

Data Index: 1565401 (Open Web Text)

Max Activating Token Index: 423

Text #16

Max Range: 2.0017. Min Range: -2.0017

Max Act: 1.8275. Min Act: -0.1700

Data Index: 1592896 (Open Web Text)

Max Activating Token Index: 294

Text #17

Max Range: 2.0017. Min Range: -2.0017

Max Act: 1.8214. Min Act: -0.1700

Data Index: 2636298 (Open Web Text)

Max Activating Token Index: 353

Text #18

Max Range: 2.0017. Min Range: -2.0017

Max Act: 1.8210. Min Act: -0.1700

Data Index: 889873 (Open Web Text)

Max Activating Token Index: 609

Text #19

Max Range: 2.0017. Min Range: -2.0017

Max Act: 1.8167. Min Act: -0.1700

Data Index: 4931584 (Open Web Text)

Max Activating Token Index: 826