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

Dataset: Open Web Text

Neuron 2225 in Layer 6

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: 4.8223. Min Range: -4.8223

Max Act: 4.8223. Min Act: -0.1700

Data Index: 5130090 (Open Web Text)

Max Activating Token Index: 662

Text #1

Max Range: 4.8223. Min Range: -4.8223

Max Act: 4.7726. Min Act: -0.1700

Data Index: 3290387 (Open Web Text)

Max Activating Token Index: 1005

Text #2

Max Range: 4.8223. Min Range: -4.8223

Max Act: 4.6720. Min Act: -0.1700

Data Index: 8515516 (Open Web Text)

Max Activating Token Index: 891

Text #3

Max Range: 4.8223. Min Range: -4.8223

Max Act: 4.6971. Min Act: -0.1700

Data Index: 887540 (Open Web Text)

Max Activating Token Index: 144

Text #4

Max Range: 4.8223. Min Range: -4.8223

Max Act: 4.7031. Min Act: -0.1700

Data Index: 5504444 (Open Web Text)

Max Activating Token Index: 179

Text #5

Max Range: 4.8223. Min Range: -4.8223

Max Act: 4.6302. Min Act: -0.1700

Data Index: 279666 (Open Web Text)

Max Activating Token Index: 874

Text #6

Max Range: 4.8223. Min Range: -4.8223

Max Act: 4.6511. Min Act: -0.1700

Data Index: 6075863 (Open Web Text)

Max Activating Token Index: 355

Text #7

Max Range: 4.8223. Min Range: -4.8223

Max Act: 4.5969. Min Act: -0.1700

Data Index: 2159991 (Open Web Text)

Max Activating Token Index: 219

Text #8

Max Range: 4.8223. Min Range: -4.8223

Max Act: 4.5912. Min Act: -0.1700

Data Index: 255243 (Open Web Text)

Max Activating Token Index: 187

Text #9

Max Range: 4.8223. Min Range: -4.8223

Max Act: 4.5844. Min Act: -0.1700

Data Index: 3900660 (Open Web Text)

Max Activating Token Index: 816

Text #10

Max Range: 4.8223. Min Range: -4.8223

Max Act: 4.5593. Min Act: -0.1700

Data Index: 8388731 (Open Web Text)

Max Activating Token Index: 801

Text #11

Max Range: 4.8223. Min Range: -4.8223

Max Act: 4.5786. Min Act: -0.1700

Data Index: 8751803 (Open Web Text)

Max Activating Token Index: 890

Text #12

Max Range: 4.8223. Min Range: -4.8223

Max Act: 4.5894. Min Act: -0.1700

Data Index: 6474405 (Open Web Text)

Max Activating Token Index: 916

Text #13

Max Range: 4.8223. Min Range: -4.8223

Max Act: 4.5823. Min Act: -0.1700

Data Index: 5885096 (Open Web Text)

Max Activating Token Index: 815

Text #14

Max Range: 4.8223. Min Range: -4.8223

Max Act: 4.5655. Min Act: -0.1700

Data Index: 2524715 (Open Web Text)

Max Activating Token Index: 487

Text #15

Max Range: 4.8223. Min Range: -4.8223

Max Act: 4.5605. Min Act: -0.1700

Data Index: 1206121 (Open Web Text)

Max Activating Token Index: 401

Text #16

Max Range: 4.8223. Min Range: -4.8223

Max Act: 4.5908. Min Act: -0.1700

Data Index: 3465876 (Open Web Text)

Max Activating Token Index: 1013

Text #17

Max Range: 4.8223. Min Range: -4.8223

Max Act: 4.5530. Min Act: -0.1700

Data Index: 8027544 (Open Web Text)

Max Activating Token Index: 958

Text #18

Max Range: 4.8223. Min Range: -4.8223

Max Act: 4.5308. Min Act: -0.1700

Data Index: 4599912 (Open Web Text)

Max Activating Token Index: 487

Text #19

Max Range: 4.8223. Min Range: -4.8223

Max Act: 4.5454. Min Act: -0.1700

Data Index: 1833605 (Open Web Text)

Max Activating Token Index: 520