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

Dataset: Open Web Text

Neuron 1301 in Layer 1

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: 4.6101. Min Range: -4.6101

Max Act: 4.5951. Min Act: -0.1700

Data Index: 3560588 (Open Web Text)

Max Activating Token Index: 548

Text #1

Max Range: 4.6101. Min Range: -4.6101

Max Act: 4.6101. Min Act: -0.1700

Data Index: 1955711 (Open Web Text)

Max Activating Token Index: 402

Text #2

Max Range: 4.6101. Min Range: -4.6101

Max Act: 4.5715. Min Act: -0.1700

Data Index: 6934830 (Open Web Text)

Max Activating Token Index: 207

Text #3

Max Range: 4.6101. Min Range: -4.6101

Max Act: 4.5869. Min Act: -0.1700

Data Index: 2357202 (Open Web Text)

Max Activating Token Index: 685

Text #4

Max Range: 4.6101. Min Range: -4.6101

Max Act: 4.5064. Min Act: -0.1700

Data Index: 7107631 (Open Web Text)

Max Activating Token Index: 927

Text #5

Max Range: 4.6101. Min Range: -4.6101

Max Act: 4.5023. Min Act: -0.1700

Data Index: 313052 (Open Web Text)

Max Activating Token Index: 434

Text #6

Max Range: 4.6101. Min Range: -4.6101

Max Act: 4.5116. Min Act: -0.1700

Data Index: 5522420 (Open Web Text)

Max Activating Token Index: 128

Text #7

Max Range: 4.6101. Min Range: -4.6101

Max Act: 4.4693. Min Act: -0.1700

Data Index: 7472427 (Open Web Text)

Max Activating Token Index: 348

Text #8

Max Range: 4.6101. Min Range: -4.6101

Max Act: 4.4486. Min Act: -0.1700

Data Index: 3641809 (Open Web Text)

Max Activating Token Index: 661

Text #9

Max Range: 4.6101. Min Range: -4.6101

Max Act: 4.4606. Min Act: -0.1700

Data Index: 7280833 (Open Web Text)

Max Activating Token Index: 164

Text #10

Max Range: 4.6101. Min Range: -4.6101

Max Act: 4.4407. Min Act: -0.1700

Data Index: 1730923 (Open Web Text)

Max Activating Token Index: 659

Text #11

Max Range: 4.6101. Min Range: -4.6101

Max Act: 4.4442. Min Act: -0.1700

Data Index: 4763432 (Open Web Text)

Max Activating Token Index: 66

Text #12

Max Range: 4.6101. Min Range: -4.6101

Max Act: 4.4429. Min Act: -0.1700

Data Index: 8019576 (Open Web Text)

Max Activating Token Index: 312

Text #13

Max Range: 4.6101. Min Range: -4.6101

Max Act: 4.4000. Min Act: -0.1700

Data Index: 5617805 (Open Web Text)

Max Activating Token Index: 540

Text #14

Max Range: 4.6101. Min Range: -4.6101

Max Act: 4.4111. Min Act: -0.1700

Data Index: 5738144 (Open Web Text)

Max Activating Token Index: 673

Text #15

Max Range: 4.6101. Min Range: -4.6101

Max Act: 4.4143. Min Act: -0.1700

Data Index: 1727292 (Open Web Text)

Max Activating Token Index: 387

Text #16

Max Range: 4.6101. Min Range: -4.6101

Max Act: 4.4214. Min Act: -0.1700

Data Index: 5953000 (Open Web Text)

Max Activating Token Index: 766

Text #17

Max Range: 4.6101. Min Range: -4.6101

Max Act: 4.4379. Min Act: -0.1700

Data Index: 836329 (Open Web Text)

Max Activating Token Index: 605

Text #18

Max Range: 4.6101. Min Range: -4.6101

Max Act: 4.4380. Min Act: -0.1700

Data Index: 1691876 (Open Web Text)

Max Activating Token Index: 122

Text #19

Max Range: 4.6101. Min Range: -4.6101

Max Act: 4.4183. Min Act: -0.1700

Data Index: 890858 (Open Web Text)

Max Activating Token Index: 183