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

Dataset: Open Web Text

Neuron 907 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: 2.9981. Min Range: -2.9981

Max Act: 2.9834. Min Act: -0.1700

Data Index: 615882 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 2.9981. Min Range: -2.9981

Max Act: 2.9981. Min Act: -0.1700

Data Index: 1093187 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 2.9981. Min Range: -2.9981

Max Act: 2.9759. Min Act: -0.1700

Data Index: 4880288 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 2.9981. Min Range: -2.9981

Max Act: 2.9691. Min Act: -0.1700

Data Index: 6182426 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 2.9981. Min Range: -2.9981

Max Act: 2.9804. Min Act: -0.1700

Data Index: 4027109 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 2.9981. Min Range: -2.9981

Max Act: 2.9681. Min Act: -0.1700

Data Index: 303149 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 2.9981. Min Range: -2.9981

Max Act: 2.9594. Min Act: -0.1700

Data Index: 1912227 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 2.9981. Min Range: -2.9981

Max Act: 2.9460. Min Act: -0.1700

Data Index: 7108269 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 2.9981. Min Range: -2.9981

Max Act: 2.9487. Min Act: -0.1700

Data Index: 4198340 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 2.9981. Min Range: -2.9981

Max Act: 2.9367. Min Act: -0.1700

Data Index: 3474654 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 2.9981. Min Range: -2.9981

Max Act: 2.9424. Min Act: -0.1700

Data Index: 4747608 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 2.9981. Min Range: -2.9981

Max Act: 2.9417. Min Act: -0.1700

Data Index: 811605 (Open Web Text)

Max Activating Token Index: 967

Text #12

Max Range: 2.9981. Min Range: -2.9981

Max Act: 2.9428. Min Act: -0.1700

Data Index: 8224211 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 2.9981. Min Range: -2.9981

Max Act: 2.9460. Min Act: -0.1700

Data Index: 1692326 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 2.9981. Min Range: -2.9981

Max Act: 2.9594. Min Act: -0.1700

Data Index: 3843580 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 2.9981. Min Range: -2.9981

Max Act: 2.9208. Min Act: -0.1700

Data Index: 931888 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 2.9981. Min Range: -2.9981

Max Act: 2.9344. Min Act: -0.1700

Data Index: 7100952 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 2.9981. Min Range: -2.9981

Max Act: 2.9286. Min Act: -0.1700

Data Index: 1229656 (Open Web Text)

Max Activating Token Index: 719

Text #18

Max Range: 2.9981. Min Range: -2.9981

Max Act: 2.9104. Min Act: -0.1700

Data Index: 4732719 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 2.9981. Min Range: -2.9981

Max Act: 2.9145. Min Act: -0.1700

Data Index: 4861881 (Open Web Text)

Max Activating Token Index: 5