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

Dataset: Open Web Text

Neuron 1412 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: 5.6348. Min Range: -5.6348

Max Act: 5.6348. Min Act: -0.1700

Data Index: 1473469 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 5.6348. Min Range: -5.6348

Max Act: 5.5025. Min Act: -0.1700

Data Index: 1614526 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 5.6348. Min Range: -5.6348

Max Act: 5.4928. Min Act: -0.1700

Data Index: 3177120 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 5.6348. Min Range: -5.6348

Max Act: 5.4605. Min Act: -0.1700

Data Index: 4698683 (Open Web Text)

Max Activating Token Index: 18

Text #4

Max Range: 5.6348. Min Range: -5.6348

Max Act: 5.4754. Min Act: -0.1700

Data Index: 3093158 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 5.6348. Min Range: -5.6348

Max Act: 5.3943. Min Act: -0.1700

Data Index: 3190964 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 5.6348. Min Range: -5.6348

Max Act: 5.3823. Min Act: -0.1700

Data Index: 4943205 (Open Web Text)

Max Activating Token Index: 19

Text #7

Max Range: 5.6348. Min Range: -5.6348

Max Act: 5.3790. Min Act: -0.1700

Data Index: 2584205 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 5.6348. Min Range: -5.6348

Max Act: 5.3793. Min Act: -0.1700

Data Index: 1132915 (Open Web Text)

Max Activating Token Index: 12

Text #9

Max Range: 5.6348. Min Range: -5.6348

Max Act: 5.3454. Min Act: -0.1700

Data Index: 1134537 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 5.6348. Min Range: -5.6348

Max Act: 5.3505. Min Act: -0.1700

Data Index: 8385234 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 5.6348. Min Range: -5.6348

Max Act: 5.3539. Min Act: -0.1700

Data Index: 1879532 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 5.6348. Min Range: -5.6348

Max Act: 5.3398. Min Act: -0.1700

Data Index: 5723425 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 5.6348. Min Range: -5.6348

Max Act: 5.3121. Min Act: -0.1700

Data Index: 6692843 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 5.6348. Min Range: -5.6348

Max Act: 5.3094. Min Act: -0.1700

Data Index: 6356744 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 5.6348. Min Range: -5.6348

Max Act: 5.3145. Min Act: -0.1700

Data Index: 4574596 (Open Web Text)

Max Activating Token Index: 20

Text #16

Max Range: 5.6348. Min Range: -5.6348

Max Act: 5.3090. Min Act: -0.1700

Data Index: 7697011 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 5.6348. Min Range: -5.6348

Max Act: 5.3020. Min Act: -0.1700

Data Index: 196403 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 5.6348. Min Range: -5.6348

Max Act: 5.3256. Min Act: -0.1700

Data Index: 1394778 (Open Web Text)

Max Activating Token Index: 9

Text #19

Max Range: 5.6348. Min Range: -5.6348

Max Act: 5.2773. Min Act: -0.1700

Data Index: 2981552 (Open Web Text)

Max Activating Token Index: 4