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

Dataset: Open Web Text

Neuron 902 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: 3.7474. Min Range: -3.7474

Max Act: 3.7203. Min Act: -0.1700

Data Index: 8522572 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.7474. Min Range: -3.7474

Max Act: 3.7307. Min Act: -0.1700

Data Index: 6635899 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 3.7474. Min Range: -3.7474

Max Act: 3.7474. Min Act: -0.1700

Data Index: 3528313 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.7474. Min Range: -3.7474

Max Act: 3.7221. Min Act: -0.1700

Data Index: 3280500 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.7474. Min Range: -3.7474

Max Act: 3.6911. Min Act: -0.1700

Data Index: 6619672 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 3.7474. Min Range: -3.7474

Max Act: 3.6898. Min Act: -0.1700

Data Index: 6580123 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.7474. Min Range: -3.7474

Max Act: 3.7024. Min Act: -0.1700

Data Index: 6549040 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.7474. Min Range: -3.7474

Max Act: 3.7123. Min Act: -0.1700

Data Index: 3576601 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 3.7474. Min Range: -3.7474

Max Act: 3.7103. Min Act: -0.1700

Data Index: 3480899 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.7474. Min Range: -3.7474

Max Act: 3.7029. Min Act: -0.1700

Data Index: 6469688 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 3.7474. Min Range: -3.7474

Max Act: 3.7022. Min Act: -0.1700

Data Index: 5984641 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 3.7474. Min Range: -3.7474

Max Act: 3.7058. Min Act: -0.1700

Data Index: 4370882 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.7474. Min Range: -3.7474

Max Act: 3.6692. Min Act: -0.1700

Data Index: 5073583 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 3.7474. Min Range: -3.7474

Max Act: 3.6732. Min Act: -0.1700

Data Index: 4200539 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 3.7474. Min Range: -3.7474

Max Act: 3.6680. Min Act: -0.1700

Data Index: 1324066 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 3.7474. Min Range: -3.7474

Max Act: 3.6773. Min Act: -0.1700

Data Index: 2152179 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 3.7474. Min Range: -3.7474

Max Act: 3.6647. Min Act: -0.1700

Data Index: 1870533 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.7474. Min Range: -3.7474

Max Act: 3.6759. Min Act: -0.1700

Data Index: 2052493 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 3.7474. Min Range: -3.7474

Max Act: 3.6566. Min Act: -0.1700

Data Index: 3648379 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 3.7474. Min Range: -3.7474

Max Act: 3.6550. Min Act: -0.1700

Data Index: 4132791 (Open Web Text)

Max Activating Token Index: 7