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

Dataset: Open Web Text

Neuron 2379 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: 5.7628. Min Range: -5.7628

Max Act: 5.7628. Min Act: -0.1700

Data Index: 7852940 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 5.7628. Min Range: -5.7628

Max Act: 5.2920. Min Act: -0.1700

Data Index: 3158029 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 5.7628. Min Range: -5.7628

Max Act: 5.2533. Min Act: -0.1700

Data Index: 2038731 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 5.7628. Min Range: -5.7628

Max Act: 5.2347. Min Act: -0.1700

Data Index: 901310 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 5.7628. Min Range: -5.7628

Max Act: 5.2477. Min Act: -0.1700

Data Index: 7444293 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 5.7628. Min Range: -5.7628

Max Act: 5.2263. Min Act: -0.1700

Data Index: 710276 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 5.7628. Min Range: -5.7628

Max Act: 5.2018. Min Act: -0.1700

Data Index: 718762 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 5.7628. Min Range: -5.7628

Max Act: 5.1980. Min Act: -0.1700

Data Index: 5753541 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 5.7628. Min Range: -5.7628

Max Act: 5.1987. Min Act: -0.1700

Data Index: 2760695 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 5.7628. Min Range: -5.7628

Max Act: 5.2048. Min Act: -0.1700

Data Index: 8158418 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 5.7628. Min Range: -5.7628

Max Act: 5.1694. Min Act: -0.1700

Data Index: 6729959 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 5.7628. Min Range: -5.7628

Max Act: 5.1734. Min Act: -0.1700

Data Index: 5702812 (Open Web Text)

Max Activating Token Index: 11

Text #12

Max Range: 5.7628. Min Range: -5.7628

Max Act: 5.1920. Min Act: -0.1700

Data Index: 4924471 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 5.7628. Min Range: -5.7628

Max Act: 5.1867. Min Act: -0.1700

Data Index: 1212192 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 5.7628. Min Range: -5.7628

Max Act: 5.1681. Min Act: -0.1700

Data Index: 799364 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 5.7628. Min Range: -5.7628

Max Act: 5.1714. Min Act: -0.1700

Data Index: 6238114 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 5.7628. Min Range: -5.7628

Max Act: 5.1880. Min Act: -0.1700

Data Index: 7017504 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 5.7628. Min Range: -5.7628

Max Act: 5.1683. Min Act: -0.1700

Data Index: 4785777 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 5.7628. Min Range: -5.7628

Max Act: 5.1611. Min Act: -0.1700

Data Index: 7348539 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 5.7628. Min Range: -5.7628

Max Act: 5.1747. Min Act: -0.1700

Data Index: 6434202 (Open Web Text)

Max Activating Token Index: 11