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

Dataset: Open Web Text

Neuron 1543 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: 1.7083. Min Range: -1.7083

Max Act: 1.7083. Min Act: -0.1700

Data Index: 115969 (Open Web Text)

Max Activating Token Index: 454

Text #1

Max Range: 1.7083. Min Range: -1.7083

Max Act: 1.6886. Min Act: -0.1700

Data Index: 6910004 (Open Web Text)

Max Activating Token Index: 618

Text #2

Max Range: 1.7083. Min Range: -1.7083

Max Act: 1.6325. Min Act: -0.1700

Data Index: 115966 (Open Web Text)

Max Activating Token Index: 481

Text #3

Max Range: 1.7083. Min Range: -1.7083

Max Act: 1.6143. Min Act: -0.1700

Data Index: 2935963 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 1.7083. Min Range: -1.7083

Max Act: 1.6113. Min Act: -0.1700

Data Index: 6434357 (Open Web Text)

Max Activating Token Index: 21

Text #5

Max Range: 1.7083. Min Range: -1.7083

Max Act: 1.6148. Min Act: -0.1700

Data Index: 7444882 (Open Web Text)

Max Activating Token Index: 455

Text #6

Max Range: 1.7083. Min Range: -1.7083

Max Act: 1.6115. Min Act: -0.1700

Data Index: 5916964 (Open Web Text)

Max Activating Token Index: 16

Text #7

Max Range: 1.7083. Min Range: -1.7083

Max Act: 1.6054. Min Act: -0.1700

Data Index: 4226411 (Open Web Text)

Max Activating Token Index: 14

Text #8

Max Range: 1.7083. Min Range: -1.7083

Max Act: 1.5962. Min Act: -0.1700

Data Index: 115968 (Open Web Text)

Max Activating Token Index: 480

Text #9

Max Range: 1.7083. Min Range: -1.7083

Max Act: 1.5914. Min Act: -0.1700

Data Index: 7231037 (Open Web Text)

Max Activating Token Index: 9

Text #10

Max Range: 1.7083. Min Range: -1.7083

Max Act: 1.5844. Min Act: -0.1700

Data Index: 1502166 (Open Web Text)

Max Activating Token Index: 9

Text #11

Max Range: 1.7083. Min Range: -1.7083

Max Act: 1.5878. Min Act: -0.1700

Data Index: 3734879 (Open Web Text)

Max Activating Token Index: 672

Text #12

Max Range: 1.7083. Min Range: -1.7083

Max Act: 1.5784. Min Act: -0.1700

Data Index: 115967 (Open Web Text)

Max Activating Token Index: 815

Text #13

Max Range: 1.7083. Min Range: -1.7083

Max Act: 1.5868. Min Act: -0.1700

Data Index: 4477540 (Open Web Text)

Max Activating Token Index: 192

Text #14

Max Range: 1.7083. Min Range: -1.7083

Max Act: 1.5813. Min Act: -0.1700

Data Index: 2645822 (Open Web Text)

Max Activating Token Index: 202

Text #15

Max Range: 1.7083. Min Range: -1.7083

Max Act: 1.5739. Min Act: -0.1700

Data Index: 8310742 (Open Web Text)

Max Activating Token Index: 128

Text #16

Max Range: 1.7083. Min Range: -1.7083

Max Act: 1.5758. Min Act: -0.1700

Data Index: 8296613 (Open Web Text)

Max Activating Token Index: 411

Text #17

Max Range: 1.7083. Min Range: -1.7083

Max Act: 1.5739. Min Act: -0.1700

Data Index: 309383 (Open Web Text)

Max Activating Token Index: 615

Text #18

Max Range: 1.7083. Min Range: -1.7083

Max Act: 1.5706. Min Act: -0.1700

Data Index: 4164922 (Open Web Text)

Max Activating Token Index: 90

Text #19

Max Range: 1.7083. Min Range: -1.7083

Max Act: 1.5704. Min Act: -0.1700

Data Index: 4635145 (Open Web Text)

Max Activating Token Index: 713