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

Dataset: Open Web Text

Neuron 405 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: 1.8389. Min Range: -1.8389

Max Act: 1.8389. Min Act: -0.1699

Data Index: 1134434 (Open Web Text)

Max Activating Token Index: 35

Text #1

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.7900. Min Act: -0.1700

Data Index: 7855731 (Open Web Text)

Max Activating Token Index: 307

Text #2

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.7995. Min Act: -0.1700

Data Index: 8562792 (Open Web Text)

Max Activating Token Index: 14

Text #3

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.7878. Min Act: -0.1699

Data Index: 811641 (Open Web Text)

Max Activating Token Index: 870

Text #4

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.7903. Min Act: -0.1697

Data Index: 2832136 (Open Web Text)

Max Activating Token Index: 800

Text #5

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.7671. Min Act: -0.1697

Data Index: 4772481 (Open Web Text)

Max Activating Token Index: 722

Text #6

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.7624. Min Act: -0.1700

Data Index: 2946686 (Open Web Text)

Max Activating Token Index: 400

Text #7

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.7657. Min Act: -0.1700

Data Index: 5645868 (Open Web Text)

Max Activating Token Index: 35

Text #8

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.7476. Min Act: -0.1699

Data Index: 811639 (Open Web Text)

Max Activating Token Index: 785

Text #9

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.7232. Min Act: -0.1694

Data Index: 4572310 (Open Web Text)

Max Activating Token Index: 669

Text #10

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.7269. Min Act: -0.1700

Data Index: 4477686 (Open Web Text)

Max Activating Token Index: 733

Text #11

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.7436. Min Act: -0.1699

Data Index: 5776912 (Open Web Text)

Max Activating Token Index: 750

Text #12

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.7051. Min Act: -0.1700

Data Index: 5541476 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.7238. Min Act: -0.1700

Data Index: 5592483 (Open Web Text)

Max Activating Token Index: 872

Text #14

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.7053. Min Act: -0.1700

Data Index: 5253340 (Open Web Text)

Max Activating Token Index: 302

Text #15

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.7051. Min Act: -0.1700

Data Index: 5253331 (Open Web Text)

Max Activating Token Index: 1014

Text #16

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.7026. Min Act: -0.1700

Data Index: 5857499 (Open Web Text)

Max Activating Token Index: 25

Text #17

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.7092. Min Act: -0.1700

Data Index: 811373 (Open Web Text)

Max Activating Token Index: 891

Text #18

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.6824. Min Act: -0.1700

Data Index: 4245346 (Open Web Text)

Max Activating Token Index: 531

Text #19

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.6840. Min Act: -0.1688

Data Index: 8310162 (Open Web Text)

Max Activating Token Index: 753