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

Dataset: Open Web Text

Neuron 518 in Layer 5

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: 2.1917. Min Range: -2.1917

Max Act: 2.1917. Min Act: -0.1700

Data Index: 2328233 (Open Web Text)

Max Activating Token Index: 131

Text #1

Max Range: 2.1917. Min Range: -2.1917

Max Act: 2.1746. Min Act: -0.1700

Data Index: 6468887 (Open Web Text)

Max Activating Token Index: 19

Text #2

Max Range: 2.1917. Min Range: -2.1917

Max Act: 2.1703. Min Act: -0.1700

Data Index: 3167571 (Open Web Text)

Max Activating Token Index: 21

Text #3

Max Range: 2.1917. Min Range: -2.1917

Max Act: 2.1506. Min Act: -0.1700

Data Index: 4562132 (Open Web Text)

Max Activating Token Index: 20

Text #4

Max Range: 2.1917. Min Range: -2.1917

Max Act: 2.1351. Min Act: -0.1700

Data Index: 3100022 (Open Web Text)

Max Activating Token Index: 41

Text #5

Max Range: 2.1917. Min Range: -2.1917

Max Act: 2.1380. Min Act: -0.1700

Data Index: 1186988 (Open Web Text)

Max Activating Token Index: 84

Text #6

Max Range: 2.1917. Min Range: -2.1917

Max Act: 2.1443. Min Act: -0.1700

Data Index: 2755375 (Open Web Text)

Max Activating Token Index: 12

Text #7

Max Range: 2.1917. Min Range: -2.1917

Max Act: 2.1402. Min Act: -0.1700

Data Index: 8420804 (Open Web Text)

Max Activating Token Index: 24

Text #8

Max Range: 2.1917. Min Range: -2.1917

Max Act: 2.1261. Min Act: -0.1700

Data Index: 3156843 (Open Web Text)

Max Activating Token Index: 13

Text #9

Max Range: 2.1917. Min Range: -2.1917

Max Act: 2.1406. Min Act: -0.1700

Data Index: 7487368 (Open Web Text)

Max Activating Token Index: 118

Text #10

Max Range: 2.1917. Min Range: -2.1917

Max Act: 2.1245. Min Act: -0.1700

Data Index: 6046809 (Open Web Text)

Max Activating Token Index: 17

Text #11

Max Range: 2.1917. Min Range: -2.1917

Max Act: 2.1113. Min Act: -0.1700

Data Index: 2884220 (Open Web Text)

Max Activating Token Index: 28

Text #12

Max Range: 2.1917. Min Range: -2.1917

Max Act: 2.1048. Min Act: -0.1700

Data Index: 7256095 (Open Web Text)

Max Activating Token Index: 25

Text #13

Max Range: 2.1917. Min Range: -2.1917

Max Act: 2.1195. Min Act: -0.1700

Data Index: 5740786 (Open Web Text)

Max Activating Token Index: 18

Text #14

Max Range: 2.1917. Min Range: -2.1917

Max Act: 2.1117. Min Act: -0.1700

Data Index: 6864815 (Open Web Text)

Max Activating Token Index: 53

Text #15

Max Range: 2.1917. Min Range: -2.1917

Max Act: 2.1132. Min Act: -0.1700

Data Index: 6935954 (Open Web Text)

Max Activating Token Index: 20

Text #16

Max Range: 2.1917. Min Range: -2.1917

Max Act: 2.0988. Min Act: -0.1700

Data Index: 3998791 (Open Web Text)

Max Activating Token Index: 32

Text #17

Max Range: 2.1917. Min Range: -2.1917

Max Act: 2.1031. Min Act: -0.1700

Data Index: 6482014 (Open Web Text)

Max Activating Token Index: 15

Text #18

Max Range: 2.1917. Min Range: -2.1917

Max Act: 2.0843. Min Act: -0.1700

Data Index: 6728076 (Open Web Text)

Max Activating Token Index: 39

Text #19

Max Range: 2.1917. Min Range: -2.1917

Max Act: 2.0967. Min Act: -0.1700

Data Index: 3995798 (Open Web Text)

Max Activating Token Index: 13