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

Dataset: Open Web Text

Neuron 542 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: 4.1579. Min Range: -4.1579

Max Act: 4.1347. Min Act: -0.1700

Data Index: 8282859 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.1579. Min Range: -4.1579

Max Act: 4.1579. Min Act: -0.1700

Data Index: 2151870 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 4.1579. Min Range: -4.1579

Max Act: 4.1302. Min Act: -0.1700

Data Index: 1982873 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 4.1579. Min Range: -4.1579

Max Act: 4.1042. Min Act: -0.1700

Data Index: 1734660 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.1579. Min Range: -4.1579

Max Act: 4.1019. Min Act: -0.1700

Data Index: 1358819 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 4.1579. Min Range: -4.1579

Max Act: 4.0964. Min Act: -0.1700

Data Index: 7959009 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 4.1579. Min Range: -4.1579

Max Act: 4.1068. Min Act: -0.1700

Data Index: 2985564 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 4.1579. Min Range: -4.1579

Max Act: 4.0884. Min Act: -0.1700

Data Index: 7226168 (Open Web Text)

Max Activating Token Index: 10

Text #8

Max Range: 4.1579. Min Range: -4.1579

Max Act: 4.1014. Min Act: -0.1700

Data Index: 1238754 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 4.1579. Min Range: -4.1579

Max Act: 4.0508. Min Act: -0.1700

Data Index: 8375274 (Open Web Text)

Max Activating Token Index: 20

Text #10

Max Range: 4.1579. Min Range: -4.1579

Max Act: 4.0589. Min Act: -0.1700

Data Index: 3335324 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 4.1579. Min Range: -4.1579

Max Act: 4.0500. Min Act: -0.1700

Data Index: 7449363 (Open Web Text)

Max Activating Token Index: 12

Text #12

Max Range: 4.1579. Min Range: -4.1579

Max Act: 4.0678. Min Act: -0.1700

Data Index: 739791 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 4.1579. Min Range: -4.1579

Max Act: 4.0510. Min Act: -0.1700

Data Index: 6645229 (Open Web Text)

Max Activating Token Index: 13

Text #14

Max Range: 4.1579. Min Range: -4.1579

Max Act: 4.0682. Min Act: -0.1700

Data Index: 6548841 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 4.1579. Min Range: -4.1579

Max Act: 4.0611. Min Act: -0.1700

Data Index: 5529659 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 4.1579. Min Range: -4.1579

Max Act: 4.0629. Min Act: -0.1700

Data Index: 2387307 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 4.1579. Min Range: -4.1579

Max Act: 4.0514. Min Act: -0.1700

Data Index: 5255140 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 4.1579. Min Range: -4.1579

Max Act: 4.0565. Min Act: -0.1700

Data Index: 3842188 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 4.1579. Min Range: -4.1579

Max Act: 4.0431. Min Act: -0.1700

Data Index: 3562559 (Open Web Text)

Max Activating Token Index: 6