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

Dataset: Open Web Text

Neuron 642 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: 3.0380. Min Range: -3.0380

Max Act: 3.0380. Min Act: -0.1700

Data Index: 5575026 (Open Web Text)

Max Activating Token Index: 709

Text #1

Max Range: 3.0380. Min Range: -3.0380

Max Act: 3.0186. Min Act: -0.1700

Data Index: 5576993 (Open Web Text)

Max Activating Token Index: 777

Text #2

Max Range: 3.0380. Min Range: -3.0380

Max Act: 3.0188. Min Act: -0.1700

Data Index: 7831069 (Open Web Text)

Max Activating Token Index: 378

Text #3

Max Range: 3.0380. Min Range: -3.0380

Max Act: 3.0087. Min Act: -0.1700

Data Index: 8759764 (Open Web Text)

Max Activating Token Index: 357

Text #4

Max Range: 3.0380. Min Range: -3.0380

Max Act: 2.9287. Min Act: -0.1700

Data Index: 1656519 (Open Web Text)

Max Activating Token Index: 470

Text #5

Max Range: 3.0380. Min Range: -3.0380

Max Act: 2.9632. Min Act: -0.1700

Data Index: 7092902 (Open Web Text)

Max Activating Token Index: 830

Text #6

Max Range: 3.0380. Min Range: -3.0380

Max Act: 2.9590. Min Act: -0.1700

Data Index: 1416477 (Open Web Text)

Max Activating Token Index: 968

Text #7

Max Range: 3.0380. Min Range: -3.0380

Max Act: 2.9046. Min Act: -0.1700

Data Index: 4063621 (Open Web Text)

Max Activating Token Index: 84

Text #8

Max Range: 3.0380. Min Range: -3.0380

Max Act: 2.9248. Min Act: -0.1700

Data Index: 3101096 (Open Web Text)

Max Activating Token Index: 564

Text #9

Max Range: 3.0380. Min Range: -3.0380

Max Act: 2.9050. Min Act: -0.1700

Data Index: 5768300 (Open Web Text)

Max Activating Token Index: 391

Text #10

Max Range: 3.0380. Min Range: -3.0380

Max Act: 2.9131. Min Act: -0.1700

Data Index: 6253754 (Open Web Text)

Max Activating Token Index: 768

Text #11

Max Range: 3.0380. Min Range: -3.0380

Max Act: 2.9039. Min Act: -0.1700

Data Index: 4844383 (Open Web Text)

Max Activating Token Index: 316

Text #12

Max Range: 3.0380. Min Range: -3.0380

Max Act: 2.8860. Min Act: -0.1700

Data Index: 2463154 (Open Web Text)

Max Activating Token Index: 306

Text #13

Max Range: 3.0380. Min Range: -3.0380

Max Act: 2.9031. Min Act: -0.1700

Data Index: 8201287 (Open Web Text)

Max Activating Token Index: 582

Text #14

Max Range: 3.0380. Min Range: -3.0380

Max Act: 2.8808. Min Act: -0.1700

Data Index: 5126923 (Open Web Text)

Max Activating Token Index: 160

Text #15

Max Range: 3.0380. Min Range: -3.0380

Max Act: 2.8954. Min Act: -0.1700

Data Index: 1760504 (Open Web Text)

Max Activating Token Index: 497

Text #16

Max Range: 3.0380. Min Range: -3.0380

Max Act: 2.8614. Min Act: -0.1700

Data Index: 2720976 (Open Web Text)

Max Activating Token Index: 172

Text #17

Max Range: 3.0380. Min Range: -3.0380

Max Act: 2.8764. Min Act: -0.1700

Data Index: 598553 (Open Web Text)

Max Activating Token Index: 781

Text #18

Max Range: 3.0380. Min Range: -3.0380

Max Act: 2.8430. Min Act: -0.1700

Data Index: 5764911 (Open Web Text)

Max Activating Token Index: 833

Text #19

Max Range: 3.0380. Min Range: -3.0380

Max Act: 2.8451. Min Act: -0.1700

Data Index: 2702277 (Open Web Text)

Max Activating Token Index: 536