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

Dataset: Open Web Text

Neuron 2888 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: 4.3544. Min Range: -4.3544

Max Act: 4.3417. Min Act: -0.1700

Data Index: 3634316 (Open Web Text)

Max Activating Token Index: 218

Text #1

Max Range: 4.3544. Min Range: -4.3544

Max Act: 4.3544. Min Act: -0.1700

Data Index: 5876608 (Open Web Text)

Max Activating Token Index: 69

Text #2

Max Range: 4.3544. Min Range: -4.3544

Max Act: 4.2764. Min Act: -0.1700

Data Index: 5747465 (Open Web Text)

Max Activating Token Index: 18

Text #3

Max Range: 4.3544. Min Range: -4.3544

Max Act: 4.2733. Min Act: -0.1700

Data Index: 6169628 (Open Web Text)

Max Activating Token Index: 665

Text #4

Max Range: 4.3544. Min Range: -4.3544

Max Act: 4.2270. Min Act: -0.1700

Data Index: 4612858 (Open Web Text)

Max Activating Token Index: 734

Text #5

Max Range: 4.3544. Min Range: -4.3544

Max Act: 4.1955. Min Act: -0.1700

Data Index: 835392 (Open Web Text)

Max Activating Token Index: 131

Text #6

Max Range: 4.3544. Min Range: -4.3544

Max Act: 4.2293. Min Act: -0.1700

Data Index: 5715120 (Open Web Text)

Max Activating Token Index: 314

Text #7

Max Range: 4.3544. Min Range: -4.3544

Max Act: 4.1912. Min Act: -0.1700

Data Index: 1177385 (Open Web Text)

Max Activating Token Index: 880

Text #8

Max Range: 4.3544. Min Range: -4.3544

Max Act: 4.2037. Min Act: -0.1700

Data Index: 4579211 (Open Web Text)

Max Activating Token Index: 25

Text #9

Max Range: 4.3544. Min Range: -4.3544

Max Act: 4.1957. Min Act: -0.1700

Data Index: 2384517 (Open Web Text)

Max Activating Token Index: 228

Text #10

Max Range: 4.3544. Min Range: -4.3544

Max Act: 4.1754. Min Act: -0.1700

Data Index: 8374312 (Open Web Text)

Max Activating Token Index: 842

Text #11

Max Range: 4.3544. Min Range: -4.3544

Max Act: 4.2021. Min Act: -0.1700

Data Index: 7729364 (Open Web Text)

Max Activating Token Index: 421

Text #12

Max Range: 4.3544. Min Range: -4.3544

Max Act: 4.1890. Min Act: -0.1700

Data Index: 7117431 (Open Web Text)

Max Activating Token Index: 131

Text #13

Max Range: 4.3544. Min Range: -4.3544

Max Act: 4.1861. Min Act: -0.1700

Data Index: 4661635 (Open Web Text)

Max Activating Token Index: 517

Text #14

Max Range: 4.3544. Min Range: -4.3544

Max Act: 4.1997. Min Act: -0.1700

Data Index: 6167592 (Open Web Text)

Max Activating Token Index: 424

Text #15

Max Range: 4.3544. Min Range: -4.3544

Max Act: 4.1400. Min Act: -0.1700

Data Index: 1189524 (Open Web Text)

Max Activating Token Index: 50

Text #16

Max Range: 4.3544. Min Range: -4.3544

Max Act: 4.1678. Min Act: -0.1700

Data Index: 2873457 (Open Web Text)

Max Activating Token Index: 30

Text #17

Max Range: 4.3544. Min Range: -4.3544

Max Act: 4.1467. Min Act: -0.1700

Data Index: 4287975 (Open Web Text)

Max Activating Token Index: 361

Text #18

Max Range: 4.3544. Min Range: -4.3544

Max Act: 4.1630. Min Act: -0.1700

Data Index: 897713 (Open Web Text)

Max Activating Token Index: 382

Text #19

Max Range: 4.3544. Min Range: -4.3544

Max Act: 4.1564. Min Act: -0.1700

Data Index: 5774970 (Open Web Text)

Max Activating Token Index: 6