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

Dataset: Open Web Text

Neuron 917 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: 1.4024. Min Range: -1.4024

Max Act: 1.4024. Min Act: -0.0467

Data Index: 3357815 (Open Web Text)

Max Activating Token Index: 985

Text #1

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.3820. Min Act: -0.0467

Data Index: 7851850 (Open Web Text)

Max Activating Token Index: 923

Text #2

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.3729. Min Act: -0.0467

Data Index: 2154742 (Open Web Text)

Max Activating Token Index: 960

Text #3

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.3788. Min Act: -0.0467

Data Index: 1483695 (Open Web Text)

Max Activating Token Index: 956

Text #4

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.3712. Min Act: -0.0467

Data Index: 2441290 (Open Web Text)

Max Activating Token Index: 973

Text #5

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.3742. Min Act: -0.0467

Data Index: 1601085 (Open Web Text)

Max Activating Token Index: 1018

Text #6

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.3799. Min Act: -0.0467

Data Index: 8035065 (Open Web Text)

Max Activating Token Index: 1001

Text #7

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.3689. Min Act: -0.0467

Data Index: 8445073 (Open Web Text)

Max Activating Token Index: 1011

Text #8

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.3766. Min Act: -0.0467

Data Index: 5403280 (Open Web Text)

Max Activating Token Index: 949

Text #9

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.3687. Min Act: -0.0467

Data Index: 3102411 (Open Web Text)

Max Activating Token Index: 973

Text #10

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.3642. Min Act: -0.0467

Data Index: 4102748 (Open Web Text)

Max Activating Token Index: 1007

Text #11

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.3679. Min Act: -0.0467

Data Index: 4744142 (Open Web Text)

Max Activating Token Index: 1001

Text #12

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.3644. Min Act: -0.0467

Data Index: 6226719 (Open Web Text)

Max Activating Token Index: 994

Text #13

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.3682. Min Act: -0.0467

Data Index: 508268 (Open Web Text)

Max Activating Token Index: 1015

Text #14

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.3627. Min Act: -0.0467

Data Index: 2128465 (Open Web Text)

Max Activating Token Index: 986

Text #15

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.3603. Min Act: -0.0467

Data Index: 6538367 (Open Web Text)

Max Activating Token Index: 993

Text #16

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.3613. Min Act: -0.0467

Data Index: 2722347 (Open Web Text)

Max Activating Token Index: 988

Text #17

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.3672. Min Act: -0.0467

Data Index: 4692948 (Open Web Text)

Max Activating Token Index: 1013

Text #18

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.3560. Min Act: -0.0467

Data Index: 1756157 (Open Web Text)

Max Activating Token Index: 1000

Text #19

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.3552. Min Act: -0.0467

Data Index: 3706156 (Open Web Text)

Max Activating Token Index: 989