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

Dataset: Open Web Text

Neuron 2545 in Layer 0

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: 3.5210. Min Range: -3.5210

Max Act: 3.5210. Min Act: -0.1700

Data Index: 8287030 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 3.5210. Min Range: -3.5210

Max Act: 3.5099. Min Act: -0.1700

Data Index: 8355981 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 3.5210. Min Range: -3.5210

Max Act: 3.4765. Min Act: -0.1700

Data Index: 5920392 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.5210. Min Range: -3.5210

Max Act: 3.4669. Min Act: -0.1700

Data Index: 645789 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 3.5210. Min Range: -3.5210

Max Act: 3.4656. Min Act: -0.1700

Data Index: 8310911 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 3.5210. Min Range: -3.5210

Max Act: 3.4669. Min Act: -0.1700

Data Index: 5138573 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 3.5210. Min Range: -3.5210

Max Act: 3.4550. Min Act: -0.1700

Data Index: 171372 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 3.5210. Min Range: -3.5210

Max Act: 3.4350. Min Act: -0.1700

Data Index: 8640571 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 3.5210. Min Range: -3.5210

Max Act: 3.4023. Min Act: -0.1700

Data Index: 8064963 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 3.5210. Min Range: -3.5210

Max Act: 3.4168. Min Act: -0.1700

Data Index: 2860182 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 3.5210. Min Range: -3.5210

Max Act: 3.3976. Min Act: -0.1700

Data Index: 3392269 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 3.5210. Min Range: -3.5210

Max Act: 3.4057. Min Act: -0.1700

Data Index: 1735839 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 3.5210. Min Range: -3.5210

Max Act: 3.4093. Min Act: -0.1700

Data Index: 4261562 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 3.5210. Min Range: -3.5210

Max Act: 3.3672. Min Act: -0.1700

Data Index: 360758 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 3.5210. Min Range: -3.5210

Max Act: 3.3896. Min Act: -0.1700

Data Index: 1634767 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 3.5210. Min Range: -3.5210

Max Act: 3.3704. Min Act: -0.1700

Data Index: 1139780 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 3.5210. Min Range: -3.5210

Max Act: 3.3854. Min Act: -0.1700

Data Index: 2485725 (Open Web Text)

Max Activating Token Index: 10

Text #17

Max Range: 3.5210. Min Range: -3.5210

Max Act: 3.3794. Min Act: -0.1700

Data Index: 8380093 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 3.5210. Min Range: -3.5210

Max Act: 3.3375. Min Act: -0.1700

Data Index: 1111052 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 3.5210. Min Range: -3.5210

Max Act: 3.3352. Min Act: -0.1700

Data Index: 4071779 (Open Web Text)

Max Activating Token Index: 5