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

Dataset: Open Web Text

Neuron 919 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: 3.6094. Min Range: -3.6094

Max Act: 3.5998. Min Act: -0.1700

Data Index: 8620396 (Open Web Text)

Max Activating Token Index: 790

Text #1

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.6072. Min Act: -0.1700

Data Index: 3633829 (Open Web Text)

Max Activating Token Index: 19

Text #2

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.6094. Min Act: -0.1700

Data Index: 3457621 (Open Web Text)

Max Activating Token Index: 740

Text #3

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.5994. Min Act: -0.1700

Data Index: 8527365 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.5985. Min Act: -0.1700

Data Index: 2484331 (Open Web Text)

Max Activating Token Index: 813

Text #5

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.5750. Min Act: -0.1700

Data Index: 7952086 (Open Web Text)

Max Activating Token Index: 49

Text #6

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.5648. Min Act: -0.1700

Data Index: 2975786 (Open Web Text)

Max Activating Token Index: 16

Text #7

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.5892. Min Act: -0.1700

Data Index: 1481741 (Open Web Text)

Max Activating Token Index: 9

Text #8

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.5793. Min Act: -0.1700

Data Index: 8487529 (Open Web Text)

Max Activating Token Index: 9

Text #9

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.5882. Min Act: -0.1700

Data Index: 6658983 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.5681. Min Act: -0.1700

Data Index: 1051432 (Open Web Text)

Max Activating Token Index: 9

Text #11

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.5848. Min Act: -0.1700

Data Index: 6341677 (Open Web Text)

Max Activating Token Index: 25

Text #12

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.5863. Min Act: -0.1700

Data Index: 3460432 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.5818. Min Act: -0.1700

Data Index: 5987804 (Open Web Text)

Max Activating Token Index: 9

Text #14

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.5559. Min Act: -0.1700

Data Index: 1703970 (Open Web Text)

Max Activating Token Index: 9

Text #15

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.5437. Min Act: -0.1700

Data Index: 3263278 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.5432. Min Act: -0.1700

Data Index: 3275541 (Open Web Text)

Max Activating Token Index: 15

Text #17

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.5595. Min Act: -0.1700

Data Index: 1800800 (Open Web Text)

Max Activating Token Index: 9

Text #18

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.5483. Min Act: -0.1700

Data Index: 3376616 (Open Web Text)

Max Activating Token Index: 24

Text #19

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.5436. Min Act: -0.1700

Data Index: 3486367 (Open Web Text)

Max Activating Token Index: 57