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

Dataset: Open Web Text

Neuron 674 in Layer 4

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: 4.5110. Min Range: -4.5110

Max Act: 4.5110. Min Act: -0.1700

Data Index: 8309739 (Open Web Text)

Max Activating Token Index: 595

Text #1

Max Range: 4.5110. Min Range: -4.5110

Max Act: 4.2138. Min Act: -0.1700

Data Index: 6510494 (Open Web Text)

Max Activating Token Index: 553

Text #2

Max Range: 4.5110. Min Range: -4.5110

Max Act: 4.1554. Min Act: -0.1700

Data Index: 6804036 (Open Web Text)

Max Activating Token Index: 180

Text #3

Max Range: 4.5110. Min Range: -4.5110

Max Act: 4.1340. Min Act: -0.1700

Data Index: 7136843 (Open Web Text)

Max Activating Token Index: 206

Text #4

Max Range: 4.5110. Min Range: -4.5110

Max Act: 4.0817. Min Act: -0.1700

Data Index: 5864809 (Open Web Text)

Max Activating Token Index: 93

Text #5

Max Range: 4.5110. Min Range: -4.5110

Max Act: 4.0479. Min Act: -0.1700

Data Index: 3154480 (Open Web Text)

Max Activating Token Index: 681

Text #6

Max Range: 4.5110. Min Range: -4.5110

Max Act: 4.0475. Min Act: -0.1700

Data Index: 6588770 (Open Web Text)

Max Activating Token Index: 850

Text #7

Max Range: 4.5110. Min Range: -4.5110

Max Act: 4.0469. Min Act: -0.1700

Data Index: 8095462 (Open Web Text)

Max Activating Token Index: 731

Text #8

Max Range: 4.5110. Min Range: -4.5110

Max Act: 4.0313. Min Act: -0.1700

Data Index: 2558079 (Open Web Text)

Max Activating Token Index: 636

Text #9

Max Range: 4.5110. Min Range: -4.5110

Max Act: 3.9900. Min Act: -0.1700

Data Index: 5575764 (Open Web Text)

Max Activating Token Index: 206

Text #10

Max Range: 4.5110. Min Range: -4.5110

Max Act: 3.9871. Min Act: -0.1700

Data Index: 1967304 (Open Web Text)

Max Activating Token Index: 345

Text #11

Max Range: 4.5110. Min Range: -4.5110

Max Act: 3.9779. Min Act: -0.1700

Data Index: 693991 (Open Web Text)

Max Activating Token Index: 102

Text #12

Max Range: 4.5110. Min Range: -4.5110

Max Act: 3.9895. Min Act: -0.1700

Data Index: 1871754 (Open Web Text)

Max Activating Token Index: 207

Text #13

Max Range: 4.5110. Min Range: -4.5110

Max Act: 3.9408. Min Act: -0.1700

Data Index: 8619997 (Open Web Text)

Max Activating Token Index: 865

Text #14

Max Range: 4.5110. Min Range: -4.5110

Max Act: 3.9256. Min Act: -0.1700

Data Index: 3820564 (Open Web Text)

Max Activating Token Index: 551

Text #15

Max Range: 4.5110. Min Range: -4.5110

Max Act: 3.9170. Min Act: -0.1700

Data Index: 2845023 (Open Web Text)

Max Activating Token Index: 784

Text #16

Max Range: 4.5110. Min Range: -4.5110

Max Act: 3.9178. Min Act: -0.1700

Data Index: 2454447 (Open Web Text)

Max Activating Token Index: 1019

Text #17

Max Range: 4.5110. Min Range: -4.5110

Max Act: 3.9495. Min Act: -0.1700

Data Index: 5244925 (Open Web Text)

Max Activating Token Index: 703

Text #18

Max Range: 4.5110. Min Range: -4.5110

Max Act: 3.9008. Min Act: -0.1700

Data Index: 7447450 (Open Web Text)

Max Activating Token Index: 507

Text #19

Max Range: 4.5110. Min Range: -4.5110

Max Act: 3.9066. Min Act: -0.1700

Data Index: 3181805 (Open Web Text)

Max Activating Token Index: 902