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

Dataset: Open Web Text

Neuron 1210 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: 3.1625. Min Range: -3.1625

Max Act: 3.1625. Min Act: -0.1700

Data Index: 7736536 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 3.1625. Min Range: -3.1625

Max Act: 3.1558. Min Act: -0.1700

Data Index: 580404 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 3.1625. Min Range: -3.1625

Max Act: 3.1523. Min Act: -0.1700

Data Index: 3134229 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 3.1625. Min Range: -3.1625

Max Act: 3.1301. Min Act: -0.1700

Data Index: 8134683 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 3.1625. Min Range: -3.1625

Max Act: 3.1172. Min Act: -0.1700

Data Index: 2609221 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 3.1625. Min Range: -3.1625

Max Act: 3.1312. Min Act: -0.1700

Data Index: 2260773 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.1625. Min Range: -3.1625

Max Act: 3.1097. Min Act: -0.1700

Data Index: 4158949 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.1625. Min Range: -3.1625

Max Act: 3.1109. Min Act: -0.1700

Data Index: 7721997 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 3.1625. Min Range: -3.1625

Max Act: 3.1108. Min Act: -0.1700

Data Index: 4418425 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.1625. Min Range: -3.1625

Max Act: 3.0986. Min Act: -0.1700

Data Index: 1252022 (Open Web Text)

Max Activating Token Index: 15

Text #10

Max Range: 3.1625. Min Range: -3.1625

Max Act: 3.1133. Min Act: -0.1700

Data Index: 5649557 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 3.1625. Min Range: -3.1625

Max Act: 3.1133. Min Act: -0.1700

Data Index: 118721 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 3.1625. Min Range: -3.1625

Max Act: 3.0970. Min Act: -0.1700

Data Index: 815732 (Open Web Text)

Max Activating Token Index: 840

Text #13

Max Range: 3.1625. Min Range: -3.1625

Max Act: 3.0992. Min Act: -0.1700

Data Index: 600900 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 3.1625. Min Range: -3.1625

Max Act: 3.0854. Min Act: -0.1700

Data Index: 6265231 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 3.1625. Min Range: -3.1625

Max Act: 3.0824. Min Act: -0.1700

Data Index: 6479652 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 3.1625. Min Range: -3.1625

Max Act: 3.0896. Min Act: -0.1700

Data Index: 3773886 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.1625. Min Range: -3.1625

Max Act: 3.0945. Min Act: -0.1700

Data Index: 1947746 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.1625. Min Range: -3.1625

Max Act: 3.0877. Min Act: -0.1700

Data Index: 7603533 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 3.1625. Min Range: -3.1625

Max Act: 3.0891. Min Act: -0.1700

Data Index: 4632468 (Open Web Text)

Max Activating Token Index: 7