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

Dataset: Open Web Text

Neuron 2734 in Layer 5

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: 3.7555. Min Range: -3.7555

Max Act: 3.7555. Min Act: -0.1700

Data Index: 2239604 (Open Web Text)

Max Activating Token Index: 916

Text #1

Max Range: 3.7555. Min Range: -3.7555

Max Act: 3.7151. Min Act: -0.1700

Data Index: 4682983 (Open Web Text)

Max Activating Token Index: 121

Text #2

Max Range: 3.7555. Min Range: -3.7555

Max Act: 3.7072. Min Act: -0.1700

Data Index: 5355826 (Open Web Text)

Max Activating Token Index: 119

Text #3

Max Range: 3.7555. Min Range: -3.7555

Max Act: 3.7060. Min Act: -0.1700

Data Index: 5030642 (Open Web Text)

Max Activating Token Index: 481

Text #4

Max Range: 3.7555. Min Range: -3.7555

Max Act: 3.6855. Min Act: -0.1700

Data Index: 6468573 (Open Web Text)

Max Activating Token Index: 403

Text #5

Max Range: 3.7555. Min Range: -3.7555

Max Act: 3.6479. Min Act: -0.1700

Data Index: 4461720 (Open Web Text)

Max Activating Token Index: 457

Text #6

Max Range: 3.7555. Min Range: -3.7555

Max Act: 3.6195. Min Act: -0.1700

Data Index: 167386 (Open Web Text)

Max Activating Token Index: 910

Text #7

Max Range: 3.7555. Min Range: -3.7555

Max Act: 3.6111. Min Act: -0.1700

Data Index: 1675280 (Open Web Text)

Max Activating Token Index: 39

Text #8

Max Range: 3.7555. Min Range: -3.7555

Max Act: 3.6103. Min Act: -0.1700

Data Index: 3247224 (Open Web Text)

Max Activating Token Index: 73

Text #9

Max Range: 3.7555. Min Range: -3.7555

Max Act: 3.6047. Min Act: -0.1700

Data Index: 3737421 (Open Web Text)

Max Activating Token Index: 42

Text #10

Max Range: 3.7555. Min Range: -3.7555

Max Act: 3.5966. Min Act: -0.1700

Data Index: 7196346 (Open Web Text)

Max Activating Token Index: 600

Text #11

Max Range: 3.7555. Min Range: -3.7555

Max Act: 3.5913. Min Act: -0.1700

Data Index: 7780192 (Open Web Text)

Max Activating Token Index: 642

Text #12

Max Range: 3.7555. Min Range: -3.7555

Max Act: 3.5643. Min Act: -0.1700

Data Index: 1241231 (Open Web Text)

Max Activating Token Index: 921

Text #13

Max Range: 3.7555. Min Range: -3.7555

Max Act: 3.5673. Min Act: -0.1700

Data Index: 4274768 (Open Web Text)

Max Activating Token Index: 28

Text #14

Max Range: 3.7555. Min Range: -3.7555

Max Act: 3.5885. Min Act: -0.1700

Data Index: 2935430 (Open Web Text)

Max Activating Token Index: 518

Text #15

Max Range: 3.7555. Min Range: -3.7555

Max Act: 3.5585. Min Act: -0.1700

Data Index: 1461391 (Open Web Text)

Max Activating Token Index: 885

Text #16

Max Range: 3.7555. Min Range: -3.7555

Max Act: 3.5579. Min Act: -0.1700

Data Index: 2490698 (Open Web Text)

Max Activating Token Index: 760

Text #17

Max Range: 3.7555. Min Range: -3.7555

Max Act: 3.5791. Min Act: -0.1700

Data Index: 5208277 (Open Web Text)

Max Activating Token Index: 378

Text #18

Max Range: 3.7555. Min Range: -3.7555

Max Act: 3.5578. Min Act: -0.1700

Data Index: 3698354 (Open Web Text)

Max Activating Token Index: 338

Text #19

Max Range: 3.7555. Min Range: -3.7555

Max Act: 3.5556. Min Act: -0.1700

Data Index: 1909647 (Open Web Text)

Max Activating Token Index: 565