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

Dataset: Open Web Text

Neuron 2890 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: 3.2866. Min Range: -3.2866

Max Act: 3.2866. Min Act: -0.1700

Data Index: 8799106 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 3.2866. Min Range: -3.2866

Max Act: 3.2162. Min Act: -0.1700

Data Index: 3489653 (Open Web Text)

Max Activating Token Index: 894

Text #2

Max Range: 3.2866. Min Range: -3.2866

Max Act: 3.2212. Min Act: -0.1700

Data Index: 1126914 (Open Web Text)

Max Activating Token Index: 375

Text #3

Max Range: 3.2866. Min Range: -3.2866

Max Act: 3.2025. Min Act: -0.1700

Data Index: 4208644 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 3.2866. Min Range: -3.2866

Max Act: 3.1915. Min Act: -0.1700

Data Index: 2453400 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.2866. Min Range: -3.2866

Max Act: 3.1837. Min Act: -0.1700

Data Index: 597088 (Open Web Text)

Max Activating Token Index: 21

Text #6

Max Range: 3.2866. Min Range: -3.2866

Max Act: 3.1754. Min Act: -0.1700

Data Index: 4699770 (Open Web Text)

Max Activating Token Index: 239

Text #7

Max Range: 3.2866. Min Range: -3.2866

Max Act: 3.1842. Min Act: -0.1700

Data Index: 6917404 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 3.2866. Min Range: -3.2866

Max Act: 3.1715. Min Act: -0.1700

Data Index: 1276557 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 3.2866. Min Range: -3.2866

Max Act: 3.1822. Min Act: -0.1700

Data Index: 4938838 (Open Web Text)

Max Activating Token Index: 13

Text #10

Max Range: 3.2866. Min Range: -3.2866

Max Act: 3.1593. Min Act: -0.1700

Data Index: 3148445 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 3.2866. Min Range: -3.2866

Max Act: 3.1564. Min Act: -0.1700

Data Index: 4555735 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 3.2866. Min Range: -3.2866

Max Act: 3.1563. Min Act: -0.1700

Data Index: 1747870 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 3.2866. Min Range: -3.2866

Max Act: 3.1592. Min Act: -0.1700

Data Index: 6849230 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 3.2866. Min Range: -3.2866

Max Act: 3.1688. Min Act: -0.1700

Data Index: 5046806 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 3.2866. Min Range: -3.2866

Max Act: 3.1566. Min Act: -0.1700

Data Index: 2320864 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 3.2866. Min Range: -3.2866

Max Act: 3.1597. Min Act: -0.1700

Data Index: 4783562 (Open Web Text)

Max Activating Token Index: 392

Text #17

Max Range: 3.2866. Min Range: -3.2866

Max Act: 3.1443. Min Act: -0.1700

Data Index: 403850 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 3.2866. Min Range: -3.2866

Max Act: 3.1507. Min Act: -0.1700

Data Index: 495922 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 3.2866. Min Range: -3.2866

Max Act: 3.1490. Min Act: -0.1700

Data Index: 1232890 (Open Web Text)

Max Activating Token Index: 8