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

Dataset: Open Web Text

Neuron 321 in Layer 3

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: 4.4410. Min Range: -4.4410

Max Act: 4.4410. Min Act: -0.1700

Data Index: 4347483 (Open Web Text)

Max Activating Token Index: 782

Text #1

Max Range: 4.4410. Min Range: -4.4410

Max Act: 4.3742. Min Act: -0.1700

Data Index: 3955052 (Open Web Text)

Max Activating Token Index: 611

Text #2

Max Range: 4.4410. Min Range: -4.4410

Max Act: 4.2842. Min Act: -0.1700

Data Index: 2677182 (Open Web Text)

Max Activating Token Index: 292

Text #3

Max Range: 4.4410. Min Range: -4.4410

Max Act: 4.3141. Min Act: -0.1700

Data Index: 81314 (Open Web Text)

Max Activating Token Index: 615

Text #4

Max Range: 4.4410. Min Range: -4.4410

Max Act: 4.2981. Min Act: -0.1700

Data Index: 2760847 (Open Web Text)

Max Activating Token Index: 469

Text #5

Max Range: 4.4410. Min Range: -4.4410

Max Act: 4.2830. Min Act: -0.1700

Data Index: 1900892 (Open Web Text)

Max Activating Token Index: 624

Text #6

Max Range: 4.4410. Min Range: -4.4410

Max Act: 4.2951. Min Act: -0.1700

Data Index: 4451126 (Open Web Text)

Max Activating Token Index: 129

Text #7

Max Range: 4.4410. Min Range: -4.4410

Max Act: 4.2502. Min Act: -0.1700

Data Index: 4914902 (Open Web Text)

Max Activating Token Index: 482

Text #8

Max Range: 4.4410. Min Range: -4.4410

Max Act: 4.2770. Min Act: -0.1700

Data Index: 1830690 (Open Web Text)

Max Activating Token Index: 48

Text #9

Max Range: 4.4410. Min Range: -4.4410

Max Act: 4.2906. Min Act: -0.1700

Data Index: 8430519 (Open Web Text)

Max Activating Token Index: 660

Text #10

Max Range: 4.4410. Min Range: -4.4410

Max Act: 4.2302. Min Act: -0.1700

Data Index: 7409629 (Open Web Text)

Max Activating Token Index: 95

Text #11

Max Range: 4.4410. Min Range: -4.4410

Max Act: 4.2029. Min Act: -0.1700

Data Index: 789856 (Open Web Text)

Max Activating Token Index: 219

Text #12

Max Range: 4.4410. Min Range: -4.4410

Max Act: 4.2387. Min Act: -0.1700

Data Index: 5234851 (Open Web Text)

Max Activating Token Index: 629

Text #13

Max Range: 4.4410. Min Range: -4.4410

Max Act: 4.2285. Min Act: -0.1700

Data Index: 2707224 (Open Web Text)

Max Activating Token Index: 14

Text #14

Max Range: 4.4410. Min Range: -4.4410

Max Act: 4.2186. Min Act: -0.1700

Data Index: 3955051 (Open Web Text)

Max Activating Token Index: 281

Text #15

Max Range: 4.4410. Min Range: -4.4410

Max Act: 4.2272. Min Act: -0.1700

Data Index: 580925 (Open Web Text)

Max Activating Token Index: 873

Text #16

Max Range: 4.4410. Min Range: -4.4410

Max Act: 4.1973. Min Act: -0.1700

Data Index: 8300929 (Open Web Text)

Max Activating Token Index: 462

Text #17

Max Range: 4.4410. Min Range: -4.4410

Max Act: 4.2406. Min Act: -0.1700

Data Index: 1677574 (Open Web Text)

Max Activating Token Index: 469

Text #18

Max Range: 4.4410. Min Range: -4.4410

Max Act: 4.1767. Min Act: -0.1700

Data Index: 4228943 (Open Web Text)

Max Activating Token Index: 327

Text #19

Max Range: 4.4410. Min Range: -4.4410

Max Act: 4.1781. Min Act: -0.1700

Data Index: 1031007 (Open Web Text)

Max Activating Token Index: 345