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

Dataset: Open Web Text

Neuron 195 in Layer 2

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: 1.7757. Min Range: -1.7757

Max Act: 1.7757. Min Act: -0.1696

Data Index: 3001130 (Open Web Text)

Max Activating Token Index: 843

Text #1

Max Range: 1.7757. Min Range: -1.7757

Max Act: 1.7303. Min Act: -0.1698

Data Index: 1265129 (Open Web Text)

Max Activating Token Index: 975

Text #2

Max Range: 1.7757. Min Range: -1.7757

Max Act: 1.7490. Min Act: -0.1700

Data Index: 8573594 (Open Web Text)

Max Activating Token Index: 220

Text #3

Max Range: 1.7757. Min Range: -1.7757

Max Act: 1.7345. Min Act: -0.1700

Data Index: 5997353 (Open Web Text)

Max Activating Token Index: 58

Text #4

Max Range: 1.7757. Min Range: -1.7757

Max Act: 1.7150. Min Act: -0.1700

Data Index: 3790000 (Open Web Text)

Max Activating Token Index: 169

Text #5

Max Range: 1.7757. Min Range: -1.7757

Max Act: 1.7147. Min Act: -0.1700

Data Index: 3390486 (Open Web Text)

Max Activating Token Index: 204

Text #6

Max Range: 1.7757. Min Range: -1.7757

Max Act: 1.7057. Min Act: -0.1700

Data Index: 3052654 (Open Web Text)

Max Activating Token Index: 594

Text #7

Max Range: 1.7757. Min Range: -1.7757

Max Act: 1.7045. Min Act: -0.1700

Data Index: 186343 (Open Web Text)

Max Activating Token Index: 178

Text #8

Max Range: 1.7757. Min Range: -1.7757

Max Act: 1.7076. Min Act: -0.1700

Data Index: 5982400 (Open Web Text)

Max Activating Token Index: 362

Text #9

Max Range: 1.7757. Min Range: -1.7757

Max Act: 1.7037. Min Act: -0.1700

Data Index: 3868630 (Open Web Text)

Max Activating Token Index: 376

Text #10

Max Range: 1.7757. Min Range: -1.7757

Max Act: 1.6997. Min Act: -0.1700

Data Index: 956609 (Open Web Text)

Max Activating Token Index: 13

Text #11

Max Range: 1.7757. Min Range: -1.7757

Max Act: 1.6921. Min Act: -0.1700

Data Index: 4076826 (Open Web Text)

Max Activating Token Index: 270

Text #12

Max Range: 1.7757. Min Range: -1.7757

Max Act: 1.7020. Min Act: -0.1700

Data Index: 5751877 (Open Web Text)

Max Activating Token Index: 65

Text #13

Max Range: 1.7757. Min Range: -1.7757

Max Act: 1.6990. Min Act: -0.1700

Data Index: 5083743 (Open Web Text)

Max Activating Token Index: 686

Text #14

Max Range: 1.7757. Min Range: -1.7757

Max Act: 1.6910. Min Act: -0.1700

Data Index: 5264151 (Open Web Text)

Max Activating Token Index: 80

Text #15

Max Range: 1.7757. Min Range: -1.7757

Max Act: 1.6905. Min Act: -0.1700

Data Index: 7785505 (Open Web Text)

Max Activating Token Index: 923

Text #16

Max Range: 1.7757. Min Range: -1.7757

Max Act: 1.6918. Min Act: -0.1700

Data Index: 7190078 (Open Web Text)

Max Activating Token Index: 49

Text #17

Max Range: 1.7757. Min Range: -1.7757

Max Act: 1.6734. Min Act: -0.1699

Data Index: 7545711 (Open Web Text)

Max Activating Token Index: 253

Text #18

Max Range: 1.7757. Min Range: -1.7757

Max Act: 1.6746. Min Act: -0.1700

Data Index: 5940683 (Open Web Text)

Max Activating Token Index: 25

Text #19

Max Range: 1.7757. Min Range: -1.7757

Max Act: 1.6799. Min Act: -0.1700

Data Index: 5630678 (Open Web Text)

Max Activating Token Index: 169