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

Dataset: Open Web Text

Neuron 1725 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: 3.8276. Min Range: -3.8276

Max Act: 3.8276. Min Act: -0.1700

Data Index: 2179607 (Open Web Text)

Max Activating Token Index: 110

Text #1

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.7927. Min Act: -0.1700

Data Index: 5267083 (Open Web Text)

Max Activating Token Index: 634

Text #2

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.7361. Min Act: -0.1700

Data Index: 2887022 (Open Web Text)

Max Activating Token Index: 866

Text #3

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.7284. Min Act: -0.1700

Data Index: 3910431 (Open Web Text)

Max Activating Token Index: 710

Text #4

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.7051. Min Act: -0.1700

Data Index: 4896599 (Open Web Text)

Max Activating Token Index: 755

Text #5

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.7116. Min Act: -0.1700

Data Index: 1271450 (Open Web Text)

Max Activating Token Index: 47

Text #6

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.7041. Min Act: -0.1700

Data Index: 2663978 (Open Web Text)

Max Activating Token Index: 831

Text #7

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.6598. Min Act: -0.1700

Data Index: 2003672 (Open Web Text)

Max Activating Token Index: 625

Text #8

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.6622. Min Act: -0.1700

Data Index: 8719443 (Open Web Text)

Max Activating Token Index: 421

Text #9

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.6606. Min Act: -0.1700

Data Index: 8639223 (Open Web Text)

Max Activating Token Index: 163

Text #10

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.6831. Min Act: -0.1700

Data Index: 6596490 (Open Web Text)

Max Activating Token Index: 53

Text #11

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.6730. Min Act: -0.1700

Data Index: 692215 (Open Web Text)

Max Activating Token Index: 486

Text #12

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.6974. Min Act: -0.1700

Data Index: 6019353 (Open Web Text)

Max Activating Token Index: 432

Text #13

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.6848. Min Act: -0.1700

Data Index: 5878730 (Open Web Text)

Max Activating Token Index: 701

Text #14

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.6299. Min Act: -0.1700

Data Index: 2362138 (Open Web Text)

Max Activating Token Index: 752

Text #15

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.6333. Min Act: -0.1700

Data Index: 2579875 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.6379. Min Act: -0.1700

Data Index: 708628 (Open Web Text)

Max Activating Token Index: 593

Text #17

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.6333. Min Act: -0.1700

Data Index: 618183 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.6358. Min Act: -0.1700

Data Index: 2610059 (Open Web Text)

Max Activating Token Index: 207

Text #19

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.6446. Min Act: -0.1700

Data Index: 4711709 (Open Web Text)

Max Activating Token Index: 612