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

Dataset: Open Web Text

Neuron 1931 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: 4.7540. Min Range: -4.7540

Max Act: 4.7540. Min Act: -0.1700

Data Index: 627299 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 4.7540. Min Range: -4.7540

Max Act: 4.7529. Min Act: -0.1700

Data Index: 4373056 (Open Web Text)

Max Activating Token Index: 26

Text #2

Max Range: 4.7540. Min Range: -4.7540

Max Act: 4.7159. Min Act: -0.1700

Data Index: 5098307 (Open Web Text)

Max Activating Token Index: 721

Text #3

Max Range: 4.7540. Min Range: -4.7540

Max Act: 4.7439. Min Act: -0.1700

Data Index: 3803997 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 4.7540. Min Range: -4.7540

Max Act: 4.7423. Min Act: -0.1700

Data Index: 3939350 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 4.7540. Min Range: -4.7540

Max Act: 4.7288. Min Act: -0.1700

Data Index: 6788327 (Open Web Text)

Max Activating Token Index: 9

Text #6

Max Range: 4.7540. Min Range: -4.7540

Max Act: 4.7190. Min Act: -0.1700

Data Index: 2691496 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 4.7540. Min Range: -4.7540

Max Act: 4.6879. Min Act: -0.1700

Data Index: 545793 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 4.7540. Min Range: -4.7540

Max Act: 4.7136. Min Act: -0.1700

Data Index: 5636395 (Open Web Text)

Max Activating Token Index: 12

Text #9

Max Range: 4.7540. Min Range: -4.7540

Max Act: 4.7110. Min Act: -0.1700

Data Index: 689190 (Open Web Text)

Max Activating Token Index: 11

Text #10

Max Range: 4.7540. Min Range: -4.7540

Max Act: 4.6818. Min Act: -0.1700

Data Index: 5543564 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 4.7540. Min Range: -4.7540

Max Act: 4.6947. Min Act: -0.1700

Data Index: 1450727 (Open Web Text)

Max Activating Token Index: 14

Text #12

Max Range: 4.7540. Min Range: -4.7540

Max Act: 4.7073. Min Act: -0.1700

Data Index: 384807 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 4.7540. Min Range: -4.7540

Max Act: 4.6792. Min Act: -0.1700

Data Index: 1013445 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 4.7540. Min Range: -4.7540

Max Act: 4.6963. Min Act: -0.1700

Data Index: 3618821 (Open Web Text)

Max Activating Token Index: 32

Text #15

Max Range: 4.7540. Min Range: -4.7540

Max Act: 4.6905. Min Act: -0.1700

Data Index: 2472974 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 4.7540. Min Range: -4.7540

Max Act: 4.7094. Min Act: -0.1700

Data Index: 2378497 (Open Web Text)

Max Activating Token Index: 16

Text #17

Max Range: 4.7540. Min Range: -4.7540

Max Act: 4.6837. Min Act: -0.1700

Data Index: 187612 (Open Web Text)

Max Activating Token Index: 677

Text #18

Max Range: 4.7540. Min Range: -4.7540

Max Act: 4.6839. Min Act: -0.1700

Data Index: 703825 (Open Web Text)

Max Activating Token Index: 17

Text #19

Max Range: 4.7540. Min Range: -4.7540

Max Act: 4.6777. Min Act: -0.1700

Data Index: 3378148 (Open Web Text)

Max Activating Token Index: 13