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

Dataset: Open Web Text

Neuron 647 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: 3.5267. Min Range: -3.5267

Max Act: 3.5267. Min Act: -0.1700

Data Index: 8486899 (Open Web Text)

Max Activating Token Index: 33

Text #1

Max Range: 3.5267. Min Range: -3.5267

Max Act: 3.4887. Min Act: -0.1700

Data Index: 3670769 (Open Web Text)

Max Activating Token Index: 654

Text #2

Max Range: 3.5267. Min Range: -3.5267

Max Act: 3.4975. Min Act: -0.1700

Data Index: 5663653 (Open Web Text)

Max Activating Token Index: 617

Text #3

Max Range: 3.5267. Min Range: -3.5267

Max Act: 3.4955. Min Act: -0.1700

Data Index: 3215780 (Open Web Text)

Max Activating Token Index: 924

Text #4

Max Range: 3.5267. Min Range: -3.5267

Max Act: 3.4803. Min Act: -0.1700

Data Index: 8796567 (Open Web Text)

Max Activating Token Index: 690

Text #5

Max Range: 3.5267. Min Range: -3.5267

Max Act: 3.4759. Min Act: -0.1700

Data Index: 686598 (Open Web Text)

Max Activating Token Index: 571

Text #6

Max Range: 3.5267. Min Range: -3.5267

Max Act: 3.4491. Min Act: -0.1700

Data Index: 6139247 (Open Web Text)

Max Activating Token Index: 395

Text #7

Max Range: 3.5267. Min Range: -3.5267

Max Act: 3.4632. Min Act: -0.1700

Data Index: 1947661 (Open Web Text)

Max Activating Token Index: 31

Text #8

Max Range: 3.5267. Min Range: -3.5267

Max Act: 3.4409. Min Act: -0.1700

Data Index: 753994 (Open Web Text)

Max Activating Token Index: 338

Text #9

Max Range: 3.5267. Min Range: -3.5267

Max Act: 3.4301. Min Act: -0.1700

Data Index: 4669179 (Open Web Text)

Max Activating Token Index: 732

Text #10

Max Range: 3.5267. Min Range: -3.5267

Max Act: 3.3955. Min Act: -0.1700

Data Index: 5200118 (Open Web Text)

Max Activating Token Index: 715

Text #11

Max Range: 3.5267. Min Range: -3.5267

Max Act: 3.4423. Min Act: -0.1700

Data Index: 2918501 (Open Web Text)

Max Activating Token Index: 245

Text #12

Max Range: 3.5267. Min Range: -3.5267

Max Act: 3.4788. Min Act: -0.1700

Data Index: 2702770 (Open Web Text)

Max Activating Token Index: 359

Text #13

Max Range: 3.5267. Min Range: -3.5267

Max Act: 3.4151. Min Act: -0.1700

Data Index: 67754 (Open Web Text)

Max Activating Token Index: 920

Text #14

Max Range: 3.5267. Min Range: -3.5267

Max Act: 3.4552. Min Act: -0.1700

Data Index: 7563072 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 3.5267. Min Range: -3.5267

Max Act: 3.4368. Min Act: -0.1700

Data Index: 7435403 (Open Web Text)

Max Activating Token Index: 273

Text #16

Max Range: 3.5267. Min Range: -3.5267

Max Act: 3.4223. Min Act: -0.1700

Data Index: 310379 (Open Web Text)

Max Activating Token Index: 225

Text #17

Max Range: 3.5267. Min Range: -3.5267

Max Act: 3.4436. Min Act: -0.1700

Data Index: 7384003 (Open Web Text)

Max Activating Token Index: 22

Text #18

Max Range: 3.5267. Min Range: -3.5267

Max Act: 3.4162. Min Act: -0.1700

Data Index: 6376253 (Open Web Text)

Max Activating Token Index: 439

Text #19

Max Range: 3.5267. Min Range: -3.5267

Max Act: 3.4260. Min Act: -0.1700

Data Index: 6001714 (Open Web Text)

Max Activating Token Index: 469