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

Dataset: Open Web Text

Neuron 843 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: 3.1908. Min Range: -3.1908

Max Act: 3.1819. Min Act: -0.1700

Data Index: 6413614 (Open Web Text)

Max Activating Token Index: 854

Text #1

Max Range: 3.1908. Min Range: -3.1908

Max Act: 3.1908. Min Act: -0.1700

Data Index: 1439390 (Open Web Text)

Max Activating Token Index: 30

Text #2

Max Range: 3.1908. Min Range: -3.1908

Max Act: 3.1741. Min Act: -0.1700

Data Index: 6068956 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.1908. Min Range: -3.1908

Max Act: 3.1750. Min Act: -0.1700

Data Index: 1568382 (Open Web Text)

Max Activating Token Index: 15

Text #4

Max Range: 3.1908. Min Range: -3.1908

Max Act: 3.1626. Min Act: -0.1700

Data Index: 6251455 (Open Web Text)

Max Activating Token Index: 1018

Text #5

Max Range: 3.1908. Min Range: -3.1908

Max Act: 3.1394. Min Act: -0.1700

Data Index: 4410950 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.1908. Min Range: -3.1908

Max Act: 3.1494. Min Act: -0.1700

Data Index: 6794946 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.1908. Min Range: -3.1908

Max Act: 3.1461. Min Act: -0.1700

Data Index: 3092520 (Open Web Text)

Max Activating Token Index: 343

Text #8

Max Range: 3.1908. Min Range: -3.1908

Max Act: 3.1305. Min Act: -0.1700

Data Index: 2738681 (Open Web Text)

Max Activating Token Index: 22

Text #9

Max Range: 3.1908. Min Range: -3.1908

Max Act: 3.1063. Min Act: -0.1700

Data Index: 324577 (Open Web Text)

Max Activating Token Index: 906

Text #10

Max Range: 3.1908. Min Range: -3.1908

Max Act: 3.1097. Min Act: -0.1700

Data Index: 5857024 (Open Web Text)

Max Activating Token Index: 17

Text #11

Max Range: 3.1908. Min Range: -3.1908

Max Act: 3.1129. Min Act: -0.1700

Data Index: 5271671 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.1908. Min Range: -3.1908

Max Act: 3.1163. Min Act: -0.1700

Data Index: 5160198 (Open Web Text)

Max Activating Token Index: 750

Text #13

Max Range: 3.1908. Min Range: -3.1908

Max Act: 3.1034. Min Act: -0.1700

Data Index: 8711014 (Open Web Text)

Max Activating Token Index: 24

Text #14

Max Range: 3.1908. Min Range: -3.1908

Max Act: 3.1261. Min Act: -0.1700

Data Index: 8100558 (Open Web Text)

Max Activating Token Index: 963

Text #15

Max Range: 3.1908. Min Range: -3.1908

Max Act: 3.1030. Min Act: -0.1700

Data Index: 4545175 (Open Web Text)

Max Activating Token Index: 71

Text #16

Max Range: 3.1908. Min Range: -3.1908

Max Act: 3.1112. Min Act: -0.1700

Data Index: 3260267 (Open Web Text)

Max Activating Token Index: 75

Text #17

Max Range: 3.1908. Min Range: -3.1908

Max Act: 3.1214. Min Act: -0.1700

Data Index: 379902 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.1908. Min Range: -3.1908

Max Act: 3.1129. Min Act: -0.1700

Data Index: 2004841 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 3.1908. Min Range: -3.1908

Max Act: 3.1110. Min Act: -0.1700

Data Index: 5438541 (Open Web Text)

Max Activating Token Index: 856