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

Dataset: Open Web Text

Neuron 2472 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: 2.7247. Min Range: -2.7247

Max Act: 2.7186. Min Act: -0.1700

Data Index: 6261376 (Open Web Text)

Max Activating Token Index: 925

Text #1

Max Range: 2.7247. Min Range: -2.7247

Max Act: 2.7247. Min Act: -0.1700

Data Index: 2502438 (Open Web Text)

Max Activating Token Index: 435

Text #2

Max Range: 2.7247. Min Range: -2.7247

Max Act: 2.6718. Min Act: -0.1700

Data Index: 2516407 (Open Web Text)

Max Activating Token Index: 181

Text #3

Max Range: 2.7247. Min Range: -2.7247

Max Act: 2.6870. Min Act: -0.1700

Data Index: 639789 (Open Web Text)

Max Activating Token Index: 82

Text #4

Max Range: 2.7247. Min Range: -2.7247

Max Act: 2.6531. Min Act: -0.1700

Data Index: 3276424 (Open Web Text)

Max Activating Token Index: 632

Text #5

Max Range: 2.7247. Min Range: -2.7247

Max Act: 2.6507. Min Act: -0.1700

Data Index: 8367826 (Open Web Text)

Max Activating Token Index: 610

Text #6

Max Range: 2.7247. Min Range: -2.7247

Max Act: 2.6338. Min Act: -0.1700

Data Index: 2818696 (Open Web Text)

Max Activating Token Index: 930

Text #7

Max Range: 2.7247. Min Range: -2.7247

Max Act: 2.6214. Min Act: -0.1700

Data Index: 571419 (Open Web Text)

Max Activating Token Index: 468

Text #8

Max Range: 2.7247. Min Range: -2.7247

Max Act: 2.6157. Min Act: -0.1700

Data Index: 2064073 (Open Web Text)

Max Activating Token Index: 880

Text #9

Max Range: 2.7247. Min Range: -2.7247

Max Act: 2.6308. Min Act: -0.1700

Data Index: 1667750 (Open Web Text)

Max Activating Token Index: 26

Text #10

Max Range: 2.7247. Min Range: -2.7247

Max Act: 2.6192. Min Act: -0.1700

Data Index: 8474529 (Open Web Text)

Max Activating Token Index: 594

Text #11

Max Range: 2.7247. Min Range: -2.7247

Max Act: 2.6342. Min Act: -0.1700

Data Index: 6929290 (Open Web Text)

Max Activating Token Index: 442

Text #12

Max Range: 2.7247. Min Range: -2.7247

Max Act: 2.6197. Min Act: -0.1700

Data Index: 1225189 (Open Web Text)

Max Activating Token Index: 166

Text #13

Max Range: 2.7247. Min Range: -2.7247

Max Act: 2.5963. Min Act: -0.1700

Data Index: 5930222 (Open Web Text)

Max Activating Token Index: 259

Text #14

Max Range: 2.7247. Min Range: -2.7247

Max Act: 2.5876. Min Act: -0.1700

Data Index: 2803409 (Open Web Text)

Max Activating Token Index: 651

Text #15

Max Range: 2.7247. Min Range: -2.7247

Max Act: 2.5888. Min Act: -0.1700

Data Index: 6297291 (Open Web Text)

Max Activating Token Index: 980

Text #16

Max Range: 2.7247. Min Range: -2.7247

Max Act: 2.5731. Min Act: -0.1700

Data Index: 319744 (Open Web Text)

Max Activating Token Index: 1017

Text #17

Max Range: 2.7247. Min Range: -2.7247

Max Act: 2.5752. Min Act: -0.1700

Data Index: 1615564 (Open Web Text)

Max Activating Token Index: 19

Text #18

Max Range: 2.7247. Min Range: -2.7247

Max Act: 2.5812. Min Act: -0.1700

Data Index: 6794744 (Open Web Text)

Max Activating Token Index: 895

Text #19

Max Range: 2.7247. Min Range: -2.7247

Max Act: 2.5860. Min Act: -0.1700

Data Index: 4522115 (Open Web Text)

Max Activating Token Index: 399