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

Dataset: Open Web Text

Neuron 567 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: 4.8910. Min Range: -4.8910

Max Act: 4.8897. Min Act: -0.1700

Data Index: 7548364 (Open Web Text)

Max Activating Token Index: 148

Text #1

Max Range: 4.8910. Min Range: -4.8910

Max Act: 4.8910. Min Act: -0.1700

Data Index: 32018 (Open Web Text)

Max Activating Token Index: 755

Text #2

Max Range: 4.8910. Min Range: -4.8910

Max Act: 4.8680. Min Act: -0.1700

Data Index: 3535670 (Open Web Text)

Max Activating Token Index: 116

Text #3

Max Range: 4.8910. Min Range: -4.8910

Max Act: 4.7922. Min Act: -0.1700

Data Index: 2673277 (Open Web Text)

Max Activating Token Index: 909

Text #4

Max Range: 4.8910. Min Range: -4.8910

Max Act: 4.8269. Min Act: -0.1700

Data Index: 6115386 (Open Web Text)

Max Activating Token Index: 695

Text #5

Max Range: 4.8910. Min Range: -4.8910

Max Act: 4.8252. Min Act: -0.1700

Data Index: 8215357 (Open Web Text)

Max Activating Token Index: 753

Text #6

Max Range: 4.8910. Min Range: -4.8910

Max Act: 4.7995. Min Act: -0.1700

Data Index: 2181701 (Open Web Text)

Max Activating Token Index: 955

Text #7

Max Range: 4.8910. Min Range: -4.8910

Max Act: 4.7716. Min Act: -0.1700

Data Index: 4427233 (Open Web Text)

Max Activating Token Index: 788

Text #8

Max Range: 4.8910. Min Range: -4.8910

Max Act: 4.7891. Min Act: -0.1700

Data Index: 8394937 (Open Web Text)

Max Activating Token Index: 610

Text #9

Max Range: 4.8910. Min Range: -4.8910

Max Act: 4.7991. Min Act: -0.1700

Data Index: 4787783 (Open Web Text)

Max Activating Token Index: 527

Text #10

Max Range: 4.8910. Min Range: -4.8910

Max Act: 4.7521. Min Act: -0.1700

Data Index: 5026378 (Open Web Text)

Max Activating Token Index: 177

Text #11

Max Range: 4.8910. Min Range: -4.8910

Max Act: 4.7505. Min Act: -0.1700

Data Index: 6248205 (Open Web Text)

Max Activating Token Index: 103

Text #12

Max Range: 4.8910. Min Range: -4.8910

Max Act: 4.7409. Min Act: -0.1700

Data Index: 3957261 (Open Web Text)

Max Activating Token Index: 113

Text #13

Max Range: 4.8910. Min Range: -4.8910

Max Act: 4.7372. Min Act: -0.1700

Data Index: 2282194 (Open Web Text)

Max Activating Token Index: 685

Text #14

Max Range: 4.8910. Min Range: -4.8910

Max Act: 4.7690. Min Act: -0.1700

Data Index: 7698551 (Open Web Text)

Max Activating Token Index: 142

Text #15

Max Range: 4.8910. Min Range: -4.8910

Max Act: 4.7672. Min Act: -0.1700

Data Index: 63186 (Open Web Text)

Max Activating Token Index: 37

Text #16

Max Range: 4.8910. Min Range: -4.8910

Max Act: 4.7370. Min Act: -0.1700

Data Index: 3567634 (Open Web Text)

Max Activating Token Index: 54

Text #17

Max Range: 4.8910. Min Range: -4.8910

Max Act: 4.7235. Min Act: -0.1700

Data Index: 1167654 (Open Web Text)

Max Activating Token Index: 576

Text #18

Max Range: 4.8910. Min Range: -4.8910

Max Act: 4.7353. Min Act: -0.1700

Data Index: 6221858 (Open Web Text)

Max Activating Token Index: 419

Text #19

Max Range: 4.8910. Min Range: -4.8910

Max Act: 4.7218. Min Act: -0.1700

Data Index: 2407501 (Open Web Text)

Max Activating Token Index: 868