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

Dataset: Open Web Text

Neuron 1701 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: 3.7492. Min Range: -3.7492

Max Act: 3.7459. Min Act: -0.1700

Data Index: 721585 (Open Web Text)

Max Activating Token Index: 32

Text #1

Max Range: 3.7492. Min Range: -3.7492

Max Act: 3.7492. Min Act: -0.1700

Data Index: 1158672 (Open Web Text)

Max Activating Token Index: 20

Text #2

Max Range: 3.7492. Min Range: -3.7492

Max Act: 3.7144. Min Act: -0.1700

Data Index: 3741044 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.7492. Min Range: -3.7492

Max Act: 3.7010. Min Act: -0.1700

Data Index: 198132 (Open Web Text)

Max Activating Token Index: 10

Text #4

Max Range: 3.7492. Min Range: -3.7492

Max Act: 3.6806. Min Act: -0.1700

Data Index: 5342849 (Open Web Text)

Max Activating Token Index: 29

Text #5

Max Range: 3.7492. Min Range: -3.7492

Max Act: 3.6923. Min Act: -0.1700

Data Index: 246362 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.7492. Min Range: -3.7492

Max Act: 3.6876. Min Act: -0.1700

Data Index: 7917053 (Open Web Text)

Max Activating Token Index: 40

Text #7

Max Range: 3.7492. Min Range: -3.7492

Max Act: 3.6638. Min Act: -0.1700

Data Index: 5578888 (Open Web Text)

Max Activating Token Index: 373

Text #8

Max Range: 3.7492. Min Range: -3.7492

Max Act: 3.6602. Min Act: -0.1700

Data Index: 8741707 (Open Web Text)

Max Activating Token Index: 942

Text #9

Max Range: 3.7492. Min Range: -3.7492

Max Act: 3.6552. Min Act: -0.1700

Data Index: 6771708 (Open Web Text)

Max Activating Token Index: 12

Text #10

Max Range: 3.7492. Min Range: -3.7492

Max Act: 3.6618. Min Act: -0.1700

Data Index: 7673809 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 3.7492. Min Range: -3.7492

Max Act: 3.6498. Min Act: -0.1700

Data Index: 214328 (Open Web Text)

Max Activating Token Index: 41

Text #12

Max Range: 3.7492. Min Range: -3.7492

Max Act: 3.6540. Min Act: -0.1700

Data Index: 7087279 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 3.7492. Min Range: -3.7492

Max Act: 3.6674. Min Act: -0.1700

Data Index: 780136 (Open Web Text)

Max Activating Token Index: 461

Text #14

Max Range: 3.7492. Min Range: -3.7492

Max Act: 3.6783. Min Act: -0.1700

Data Index: 403598 (Open Web Text)

Max Activating Token Index: 582

Text #15

Max Range: 3.7492. Min Range: -3.7492

Max Act: 3.6312. Min Act: -0.1700

Data Index: 2214770 (Open Web Text)

Max Activating Token Index: 31

Text #16

Max Range: 3.7492. Min Range: -3.7492

Max Act: 3.6312. Min Act: -0.1700

Data Index: 2387884 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 3.7492. Min Range: -3.7492

Max Act: 3.6357. Min Act: -0.1700

Data Index: 5862732 (Open Web Text)

Max Activating Token Index: 24

Text #18

Max Range: 3.7492. Min Range: -3.7492

Max Act: 3.6298. Min Act: -0.1700

Data Index: 4824269 (Open Web Text)

Max Activating Token Index: 70

Text #19

Max Range: 3.7492. Min Range: -3.7492

Max Act: 3.6329. Min Act: -0.1700

Data Index: 7102402 (Open Web Text)

Max Activating Token Index: 58