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

Dataset: Open Web Text

Neuron 1575 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: 3.8671. Min Range: -3.8671

Max Act: 3.8671. Min Act: -0.1700

Data Index: 6268458 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 3.8671. Min Range: -3.8671

Max Act: 3.8437. Min Act: -0.1700

Data Index: 575454 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 3.8671. Min Range: -3.8671

Max Act: 3.8086. Min Act: -0.1700

Data Index: 8314665 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.8671. Min Range: -3.8671

Max Act: 3.8380. Min Act: -0.1700

Data Index: 3189335 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 3.8671. Min Range: -3.8671

Max Act: 3.8148. Min Act: -0.1700

Data Index: 5653343 (Open Web Text)

Max Activating Token Index: 13

Text #5

Max Range: 3.8671. Min Range: -3.8671

Max Act: 3.8122. Min Act: -0.1700

Data Index: 4872937 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 3.8671. Min Range: -3.8671

Max Act: 3.8011. Min Act: -0.1700

Data Index: 7924061 (Open Web Text)

Max Activating Token Index: 19

Text #7

Max Range: 3.8671. Min Range: -3.8671

Max Act: 3.7934. Min Act: -0.1700

Data Index: 8452903 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 3.8671. Min Range: -3.8671

Max Act: 3.7785. Min Act: -0.1700

Data Index: 701641 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 3.8671. Min Range: -3.8671

Max Act: 3.7957. Min Act: -0.1700

Data Index: 1263600 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 3.8671. Min Range: -3.8671

Max Act: 3.7771. Min Act: -0.1700

Data Index: 1341072 (Open Web Text)

Max Activating Token Index: 10

Text #11

Max Range: 3.8671. Min Range: -3.8671

Max Act: 3.7879. Min Act: -0.1700

Data Index: 4186657 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 3.8671. Min Range: -3.8671

Max Act: 3.7902. Min Act: -0.1700

Data Index: 1690485 (Open Web Text)

Max Activating Token Index: 907

Text #13

Max Range: 3.8671. Min Range: -3.8671

Max Act: 3.7920. Min Act: -0.1700

Data Index: 5543147 (Open Web Text)

Max Activating Token Index: 10

Text #14

Max Range: 3.8671. Min Range: -3.8671

Max Act: 3.7761. Min Act: -0.1700

Data Index: 577947 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 3.8671. Min Range: -3.8671

Max Act: 3.7544. Min Act: -0.1700

Data Index: 2254942 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 3.8671. Min Range: -3.8671

Max Act: 3.7563. Min Act: -0.1700

Data Index: 2016620 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.8671. Min Range: -3.8671

Max Act: 3.7519. Min Act: -0.1700

Data Index: 4553220 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.8671. Min Range: -3.8671

Max Act: 3.7541. Min Act: -0.1700

Data Index: 1409980 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 3.8671. Min Range: -3.8671

Max Act: 3.7710. Min Act: -0.1700

Data Index: 255075 (Open Web Text)

Max Activating Token Index: 4