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

Dataset: Open Web Text

Neuron 1084 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: 1.9644. Min Range: -1.9644

Max Act: 1.9644. Min Act: -0.1700

Data Index: 2197019 (Open Web Text)

Max Activating Token Index: 148

Text #1

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.9406. Min Act: -0.1700

Data Index: 841767 (Open Web Text)

Max Activating Token Index: 528

Text #2

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.9202. Min Act: -0.1700

Data Index: 2130856 (Open Web Text)

Max Activating Token Index: 250

Text #3

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.9149. Min Act: -0.1700

Data Index: 1269075 (Open Web Text)

Max Activating Token Index: 135

Text #4

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.9029. Min Act: -0.1700

Data Index: 2952039 (Open Web Text)

Max Activating Token Index: 87

Text #5

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.8850. Min Act: -0.1700

Data Index: 570368 (Open Web Text)

Max Activating Token Index: 319

Text #6

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.8841. Min Act: -0.1700

Data Index: 2921906 (Open Web Text)

Max Activating Token Index: 543

Text #7

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.8753. Min Act: -0.1700

Data Index: 4687175 (Open Web Text)

Max Activating Token Index: 382

Text #8

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.8736. Min Act: -0.1700

Data Index: 6049208 (Open Web Text)

Max Activating Token Index: 166

Text #9

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.8760. Min Act: -0.1700

Data Index: 2714503 (Open Web Text)

Max Activating Token Index: 913

Text #10

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.8586. Min Act: -0.1700

Data Index: 3219169 (Open Web Text)

Max Activating Token Index: 985

Text #11

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.8601. Min Act: -0.1700

Data Index: 5688854 (Open Web Text)

Max Activating Token Index: 493

Text #12

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.8697. Min Act: -0.1700

Data Index: 7319488 (Open Web Text)

Max Activating Token Index: 79

Text #13

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.8672. Min Act: -0.1700

Data Index: 8255898 (Open Web Text)

Max Activating Token Index: 114

Text #14

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.8507. Min Act: -0.1700

Data Index: 2855332 (Open Web Text)

Max Activating Token Index: 78

Text #15

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.8587. Min Act: -0.1700

Data Index: 7552618 (Open Web Text)

Max Activating Token Index: 47

Text #16

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.8571. Min Act: -0.1700

Data Index: 2103714 (Open Web Text)

Max Activating Token Index: 133

Text #17

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.8622. Min Act: -0.1700

Data Index: 7019518 (Open Web Text)

Max Activating Token Index: 429

Text #18

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.8510. Min Act: -0.1700

Data Index: 100002 (Open Web Text)

Max Activating Token Index: 536

Text #19

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.8386. Min Act: -0.1700

Data Index: 915119 (Open Web Text)

Max Activating Token Index: 672