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

Dataset: Open Web Text

Neuron 2371 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: 5.1621. Min Range: -5.1621

Max Act: 5.1621. Min Act: -0.1700

Data Index: 1516388 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 5.1621. Min Range: -5.1621

Max Act: 5.0421. Min Act: -0.1700

Data Index: 5033685 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 5.1621. Min Range: -5.1621

Max Act: 5.0321. Min Act: -0.1700

Data Index: 3699705 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 5.1621. Min Range: -5.1621

Max Act: 5.0000. Min Act: -0.1700

Data Index: 5527831 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 5.1621. Min Range: -5.1621

Max Act: 5.0085. Min Act: -0.1700

Data Index: 1132999 (Open Web Text)

Max Activating Token Index: 10

Text #5

Max Range: 5.1621. Min Range: -5.1621

Max Act: 4.9771. Min Act: -0.1700

Data Index: 3142410 (Open Web Text)

Max Activating Token Index: 16

Text #6

Max Range: 5.1621. Min Range: -5.1621

Max Act: 4.9773. Min Act: -0.1700

Data Index: 712009 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 5.1621. Min Range: -5.1621

Max Act: 4.9790. Min Act: -0.1700

Data Index: 2962173 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 5.1621. Min Range: -5.1621

Max Act: 4.9712. Min Act: -0.1700

Data Index: 4461730 (Open Web Text)

Max Activating Token Index: 12

Text #9

Max Range: 5.1621. Min Range: -5.1621

Max Act: 5.0008. Min Act: -0.1700

Data Index: 3753935 (Open Web Text)

Max Activating Token Index: 13

Text #10

Max Range: 5.1621. Min Range: -5.1621

Max Act: 4.9805. Min Act: -0.1700

Data Index: 3415919 (Open Web Text)

Max Activating Token Index: 15

Text #11

Max Range: 5.1621. Min Range: -5.1621

Max Act: 4.9761. Min Act: -0.1699

Data Index: 812560 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 5.1621. Min Range: -5.1621

Max Act: 4.9473. Min Act: -0.1700

Data Index: 3481551 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 5.1621. Min Range: -5.1621

Max Act: 4.9523. Min Act: -0.1700

Data Index: 515103 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 5.1621. Min Range: -5.1621

Max Act: 4.9535. Min Act: -0.1700

Data Index: 1155970 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 5.1621. Min Range: -5.1621

Max Act: 4.9609. Min Act: -0.1700

Data Index: 3946062 (Open Web Text)

Max Activating Token Index: 9

Text #16

Max Range: 5.1621. Min Range: -5.1621

Max Act: 4.9572. Min Act: -0.1700

Data Index: 408892 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 5.1621. Min Range: -5.1621

Max Act: 4.9815. Min Act: -0.1700

Data Index: 3307296 (Open Web Text)

Max Activating Token Index: 15

Text #18

Max Range: 5.1621. Min Range: -5.1621

Max Act: 4.9565. Min Act: -0.1700

Data Index: 946280 (Open Web Text)

Max Activating Token Index: 18

Text #19

Max Range: 5.1621. Min Range: -5.1621

Max Act: 4.9571. Min Act: -0.1700

Data Index: 4584067 (Open Web Text)

Max Activating Token Index: 8