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

Dataset: Open Web Text

Neuron 897 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: 2.1968. Min Range: -2.1968

Max Act: 2.1968. Min Act: -0.1700

Data Index: 3556726 (Open Web Text)

Max Activating Token Index: 390

Text #1

Max Range: 2.1968. Min Range: -2.1968

Max Act: 2.1530. Min Act: -0.1695

Data Index: 3556725 (Open Web Text)

Max Activating Token Index: 879

Text #2

Max Range: 2.1968. Min Range: -2.1968

Max Act: 2.1376. Min Act: -0.1700

Data Index: 3556722 (Open Web Text)

Max Activating Token Index: 448

Text #3

Max Range: 2.1968. Min Range: -2.1968

Max Act: 2.1310. Min Act: -0.1699

Data Index: 4191734 (Open Web Text)

Max Activating Token Index: 886

Text #4

Max Range: 2.1968. Min Range: -2.1968

Max Act: 2.1213. Min Act: -0.1700

Data Index: 3556721 (Open Web Text)

Max Activating Token Index: 944

Text #5

Max Range: 2.1968. Min Range: -2.1968

Max Act: 2.1165. Min Act: -0.1700

Data Index: 3233330 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 2.1968. Min Range: -2.1968

Max Act: 2.1240. Min Act: -0.1700

Data Index: 2196290 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 2.1968. Min Range: -2.1968

Max Act: 2.1053. Min Act: -0.1700

Data Index: 6885180 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 2.1968. Min Range: -2.1968

Max Act: 2.1049. Min Act: -0.1700

Data Index: 4257493 (Open Web Text)

Max Activating Token Index: 640

Text #9

Max Range: 2.1968. Min Range: -2.1968

Max Act: 2.0931. Min Act: -0.1699

Data Index: 4191764 (Open Web Text)

Max Activating Token Index: 114

Text #10

Max Range: 2.1968. Min Range: -2.1968

Max Act: 2.0867. Min Act: -0.1700

Data Index: 6575932 (Open Web Text)

Max Activating Token Index: 791

Text #11

Max Range: 2.1968. Min Range: -2.1968

Max Act: 2.0747. Min Act: -0.1700

Data Index: 7091542 (Open Web Text)

Max Activating Token Index: 966

Text #12

Max Range: 2.1968. Min Range: -2.1968

Max Act: 2.0897. Min Act: -0.1700

Data Index: 8376653 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 2.1968. Min Range: -2.1968

Max Act: 2.0601. Min Act: -0.1700

Data Index: 648976 (Open Web Text)

Max Activating Token Index: 428

Text #14

Max Range: 2.1968. Min Range: -2.1968

Max Act: 2.0521. Min Act: -0.1700

Data Index: 6477281 (Open Web Text)

Max Activating Token Index: 932

Text #15

Max Range: 2.1968. Min Range: -2.1968

Max Act: 2.0653. Min Act: -0.1700

Data Index: 4704114 (Open Web Text)

Max Activating Token Index: 619

Text #16

Max Range: 2.1968. Min Range: -2.1968

Max Act: 2.0683. Min Act: -0.1700

Data Index: 5830187 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 2.1968. Min Range: -2.1968

Max Act: 2.0661. Min Act: -0.1700

Data Index: 1774022 (Open Web Text)

Max Activating Token Index: 338

Text #18

Max Range: 2.1968. Min Range: -2.1968

Max Act: 2.0658. Min Act: -0.1700

Data Index: 5362755 (Open Web Text)

Max Activating Token Index: 390

Text #19

Max Range: 2.1968. Min Range: -2.1968

Max Act: 2.0658. Min Act: -0.1700

Data Index: 2274652 (Open Web Text)

Max Activating Token Index: 559