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

Dataset: Open Web Text

Neuron 859 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: 1.4420. Min Range: -1.4420

Max Act: 1.4388. Min Act: -0.1700

Data Index: 5721281 (Open Web Text)

Max Activating Token Index: 116

Text #1

Max Range: 1.4420. Min Range: -1.4420

Max Act: 1.4420. Min Act: -0.1673

Data Index: 4289033 (Open Web Text)

Max Activating Token Index: 90

Text #2

Max Range: 1.4420. Min Range: -1.4420

Max Act: 1.4247. Min Act: -0.1700

Data Index: 674257 (Open Web Text)

Max Activating Token Index: 407

Text #3

Max Range: 1.4420. Min Range: -1.4420

Max Act: 1.4019. Min Act: -0.1675

Data Index: 6054008 (Open Web Text)

Max Activating Token Index: 66

Text #4

Max Range: 1.4420. Min Range: -1.4420

Max Act: 1.4035. Min Act: -0.1688

Data Index: 2460858 (Open Web Text)

Max Activating Token Index: 68

Text #5

Max Range: 1.4420. Min Range: -1.4420

Max Act: 1.4053. Min Act: -0.1658

Data Index: 8233713 (Open Web Text)

Max Activating Token Index: 58

Text #6

Max Range: 1.4420. Min Range: -1.4420

Max Act: 1.3947. Min Act: -0.1632

Data Index: 7698978 (Open Web Text)

Max Activating Token Index: 675

Text #7

Max Range: 1.4420. Min Range: -1.4420

Max Act: 1.3966. Min Act: -0.1698

Data Index: 1896161 (Open Web Text)

Max Activating Token Index: 101

Text #8

Max Range: 1.4420. Min Range: -1.4420

Max Act: 1.3990. Min Act: -0.1649

Data Index: 5701187 (Open Web Text)

Max Activating Token Index: 397

Text #9

Max Range: 1.4420. Min Range: -1.4420

Max Act: 1.3955. Min Act: -0.1695

Data Index: 2501138 (Open Web Text)

Max Activating Token Index: 421

Text #10

Max Range: 1.4420. Min Range: -1.4420

Max Act: 1.3846. Min Act: -0.1700

Data Index: 4063753 (Open Web Text)

Max Activating Token Index: 98

Text #11

Max Range: 1.4420. Min Range: -1.4420

Max Act: 1.3810. Min Act: -0.1600

Data Index: 4858365 (Open Web Text)

Max Activating Token Index: 129

Text #12

Max Range: 1.4420. Min Range: -1.4420

Max Act: 1.3895. Min Act: -0.1700

Data Index: 7852982 (Open Web Text)

Max Activating Token Index: 115

Text #13

Max Range: 1.4420. Min Range: -1.4420

Max Act: 1.3776. Min Act: -0.1692

Data Index: 5077704 (Open Web Text)

Max Activating Token Index: 193

Text #14

Max Range: 1.4420. Min Range: -1.4420

Max Act: 1.3750. Min Act: -0.1631

Data Index: 6800244 (Open Web Text)

Max Activating Token Index: 670

Text #15

Max Range: 1.4420. Min Range: -1.4420

Max Act: 1.3873. Min Act: -0.1696

Data Index: 4481737 (Open Web Text)

Max Activating Token Index: 369

Text #16

Max Range: 1.4420. Min Range: -1.4420

Max Act: 1.3742. Min Act: -0.1646

Data Index: 5920895 (Open Web Text)

Max Activating Token Index: 91

Text #17

Max Range: 1.4420. Min Range: -1.4420

Max Act: 1.3662. Min Act: -0.1667

Data Index: 7290109 (Open Web Text)

Max Activating Token Index: 102

Text #18

Max Range: 1.4420. Min Range: -1.4420

Max Act: 1.3667. Min Act: -0.1682

Data Index: 2270378 (Open Web Text)

Max Activating Token Index: 1020

Text #19

Max Range: 1.4420. Min Range: -1.4420

Max Act: 1.3719. Min Act: -0.1699

Data Index: 4292240 (Open Web Text)

Max Activating Token Index: 478