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

Dataset: Open Web Text

Neuron 1285 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: 6.3814. Min Range: -6.3814

Max Act: 6.3814. Min Act: -0.1700

Data Index: 8445812 (Open Web Text)

Max Activating Token Index: 807

Text #1

Max Range: 6.3814. Min Range: -6.3814

Max Act: 6.0455. Min Act: -0.1700

Data Index: 7877079 (Open Web Text)

Max Activating Token Index: 594

Text #2

Max Range: 6.3814. Min Range: -6.3814

Max Act: 5.9113. Min Act: -0.1700

Data Index: 6224088 (Open Web Text)

Max Activating Token Index: 150

Text #3

Max Range: 6.3814. Min Range: -6.3814

Max Act: 5.8859. Min Act: -0.1700

Data Index: 8171601 (Open Web Text)

Max Activating Token Index: 47

Text #4

Max Range: 6.3814. Min Range: -6.3814

Max Act: 5.9198. Min Act: -0.1700

Data Index: 1519650 (Open Web Text)

Max Activating Token Index: 638

Text #5

Max Range: 6.3814. Min Range: -6.3814

Max Act: 5.8450. Min Act: -0.1700

Data Index: 6684920 (Open Web Text)

Max Activating Token Index: 689

Text #6

Max Range: 6.3814. Min Range: -6.3814

Max Act: 5.8287. Min Act: -0.1700

Data Index: 3405543 (Open Web Text)

Max Activating Token Index: 323

Text #7

Max Range: 6.3814. Min Range: -6.3814

Max Act: 5.8329. Min Act: -0.1700

Data Index: 2942003 (Open Web Text)

Max Activating Token Index: 771

Text #8

Max Range: 6.3814. Min Range: -6.3814

Max Act: 5.7933. Min Act: -0.1700

Data Index: 6003632 (Open Web Text)

Max Activating Token Index: 922

Text #9

Max Range: 6.3814. Min Range: -6.3814

Max Act: 5.7660. Min Act: -0.1700

Data Index: 4391393 (Open Web Text)

Max Activating Token Index: 488

Text #10

Max Range: 6.3814. Min Range: -6.3814

Max Act: 5.7385. Min Act: -0.1700

Data Index: 6431140 (Open Web Text)

Max Activating Token Index: 768

Text #11

Max Range: 6.3814. Min Range: -6.3814

Max Act: 5.7322. Min Act: -0.1700

Data Index: 8075402 (Open Web Text)

Max Activating Token Index: 925

Text #12

Max Range: 6.3814. Min Range: -6.3814

Max Act: 5.7009. Min Act: -0.1700

Data Index: 202408 (Open Web Text)

Max Activating Token Index: 611

Text #13

Max Range: 6.3814. Min Range: -6.3814

Max Act: 5.6242. Min Act: -0.1700

Data Index: 1597566 (Open Web Text)

Max Activating Token Index: 66

Text #14

Max Range: 6.3814. Min Range: -6.3814

Max Act: 5.6400. Min Act: -0.1700

Data Index: 69794 (Open Web Text)

Max Activating Token Index: 887

Text #15

Max Range: 6.3814. Min Range: -6.3814

Max Act: 5.6498. Min Act: -0.1700

Data Index: 2201292 (Open Web Text)

Max Activating Token Index: 383

Text #16

Max Range: 6.3814. Min Range: -6.3814

Max Act: 5.6744. Min Act: -0.1700

Data Index: 4350739 (Open Web Text)

Max Activating Token Index: 891

Text #17

Max Range: 6.3814. Min Range: -6.3814

Max Act: 5.6083. Min Act: -0.1700

Data Index: 5160569 (Open Web Text)

Max Activating Token Index: 393

Text #18

Max Range: 6.3814. Min Range: -6.3814

Max Act: 5.5879. Min Act: -0.1700

Data Index: 2245386 (Open Web Text)

Max Activating Token Index: 587

Text #19

Max Range: 6.3814. Min Range: -6.3814

Max Act: 5.5714. Min Act: -0.1700

Data Index: 6301340 (Open Web Text)

Max Activating Token Index: 314