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

Dataset: Open Web Text

Neuron 1650 in Layer 2

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: 4.5692. Min Range: -4.5692

Max Act: 4.5692. Min Act: -0.1700

Data Index: 951442 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 4.5692. Min Range: -4.5692

Max Act: 4.5380. Min Act: -0.1700

Data Index: 8294868 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 4.5692. Min Range: -4.5692

Max Act: 4.4646. Min Act: -0.1700

Data Index: 7901762 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 4.5692. Min Range: -4.5692

Max Act: 4.4495. Min Act: -0.1700

Data Index: 4602015 (Open Web Text)

Max Activating Token Index: 541

Text #4

Max Range: 4.5692. Min Range: -4.5692

Max Act: 4.4321. Min Act: -0.1700

Data Index: 7458448 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 4.5692. Min Range: -4.5692

Max Act: 4.4468. Min Act: -0.1700

Data Index: 3644793 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 4.5692. Min Range: -4.5692

Max Act: 4.4348. Min Act: -0.1700

Data Index: 2854533 (Open Web Text)

Max Activating Token Index: 9

Text #7

Max Range: 4.5692. Min Range: -4.5692

Max Act: 4.3896. Min Act: -0.1700

Data Index: 2404235 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 4.5692. Min Range: -4.5692

Max Act: 4.4136. Min Act: -0.1700

Data Index: 1607045 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 4.5692. Min Range: -4.5692

Max Act: 4.3944. Min Act: -0.1700

Data Index: 6519818 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 4.5692. Min Range: -4.5692

Max Act: 4.4194. Min Act: -0.1700

Data Index: 2366242 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 4.5692. Min Range: -4.5692

Max Act: 4.4030. Min Act: -0.1700

Data Index: 3703491 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 4.5692. Min Range: -4.5692

Max Act: 4.3922. Min Act: -0.1700

Data Index: 8269009 (Open Web Text)

Max Activating Token Index: 371

Text #13

Max Range: 4.5692. Min Range: -4.5692

Max Act: 4.4136. Min Act: -0.1700

Data Index: 1501534 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 4.5692. Min Range: -4.5692

Max Act: 4.3820. Min Act: -0.1700

Data Index: 5323772 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 4.5692. Min Range: -4.5692

Max Act: 4.3779. Min Act: -0.1700

Data Index: 5589265 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 4.5692. Min Range: -4.5692

Max Act: 4.3794. Min Act: -0.1700

Data Index: 3475095 (Open Web Text)

Max Activating Token Index: 721

Text #17

Max Range: 4.5692. Min Range: -4.5692

Max Act: 4.3765. Min Act: -0.1700

Data Index: 7038271 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 4.5692. Min Range: -4.5692

Max Act: 4.3672. Min Act: -0.1700

Data Index: 1479988 (Open Web Text)

Max Activating Token Index: 504

Text #19

Max Range: 4.5692. Min Range: -4.5692

Max Act: 4.3765. Min Act: -0.1700

Data Index: 7375305 (Open Web Text)

Max Activating Token Index: 3