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

Dataset: Open Web Text

Neuron 206 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: 6.4949. Min Range: -6.4949

Max Act: 6.4949. Min Act: -0.1700

Data Index: 4216079 (Open Web Text)

Max Activating Token Index: 517

Text #1

Max Range: 6.4949. Min Range: -6.4949

Max Act: 6.3839. Min Act: -0.1700

Data Index: 4587934 (Open Web Text)

Max Activating Token Index: 365

Text #2

Max Range: 6.4949. Min Range: -6.4949

Max Act: 6.3065. Min Act: -0.1700

Data Index: 8204708 (Open Web Text)

Max Activating Token Index: 550

Text #3

Max Range: 6.4949. Min Range: -6.4949

Max Act: 6.2927. Min Act: -0.1700

Data Index: 7533566 (Open Web Text)

Max Activating Token Index: 777

Text #4

Max Range: 6.4949. Min Range: -6.4949

Max Act: 6.2671. Min Act: -0.1700

Data Index: 4845042 (Open Web Text)

Max Activating Token Index: 899

Text #5

Max Range: 6.4949. Min Range: -6.4949

Max Act: 6.2085. Min Act: -0.1700

Data Index: 150155 (Open Web Text)

Max Activating Token Index: 301

Text #6

Max Range: 6.4949. Min Range: -6.4949

Max Act: 6.2601. Min Act: -0.1700

Data Index: 5440492 (Open Web Text)

Max Activating Token Index: 845

Text #7

Max Range: 6.4949. Min Range: -6.4949

Max Act: 6.2916. Min Act: -0.1700

Data Index: 5930061 (Open Web Text)

Max Activating Token Index: 108

Text #8

Max Range: 6.4949. Min Range: -6.4949

Max Act: 6.1760. Min Act: -0.1700

Data Index: 7772562 (Open Web Text)

Max Activating Token Index: 873

Text #9

Max Range: 6.4949. Min Range: -6.4949

Max Act: 6.1707. Min Act: -0.1700

Data Index: 5154216 (Open Web Text)

Max Activating Token Index: 376

Text #10

Max Range: 6.4949. Min Range: -6.4949

Max Act: 6.2036. Min Act: -0.1700

Data Index: 2058323 (Open Web Text)

Max Activating Token Index: 486

Text #11

Max Range: 6.4949. Min Range: -6.4949

Max Act: 6.1644. Min Act: -0.1700

Data Index: 3617454 (Open Web Text)

Max Activating Token Index: 994

Text #12

Max Range: 6.4949. Min Range: -6.4949

Max Act: 6.1599. Min Act: -0.1700

Data Index: 630511 (Open Web Text)

Max Activating Token Index: 933

Text #13

Max Range: 6.4949. Min Range: -6.4949

Max Act: 6.1929. Min Act: -0.1700

Data Index: 915958 (Open Web Text)

Max Activating Token Index: 613

Text #14

Max Range: 6.4949. Min Range: -6.4949

Max Act: 6.1758. Min Act: -0.1700

Data Index: 6195947 (Open Web Text)

Max Activating Token Index: 300

Text #15

Max Range: 6.4949. Min Range: -6.4949

Max Act: 6.1194. Min Act: -0.1700

Data Index: 3146985 (Open Web Text)

Max Activating Token Index: 291

Text #16

Max Range: 6.4949. Min Range: -6.4949

Max Act: 6.1883. Min Act: -0.1700

Data Index: 5522000 (Open Web Text)

Max Activating Token Index: 829

Text #17

Max Range: 6.4949. Min Range: -6.4949

Max Act: 6.1196. Min Act: -0.1700

Data Index: 2794805 (Open Web Text)

Max Activating Token Index: 414

Text #18

Max Range: 6.4949. Min Range: -6.4949

Max Act: 6.1148. Min Act: -0.1700

Data Index: 6130738 (Open Web Text)

Max Activating Token Index: 925

Text #19

Max Range: 6.4949. Min Range: -6.4949

Max Act: 6.1685. Min Act: -0.1700

Data Index: 1955916 (Open Web Text)

Max Activating Token Index: 975