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

Dataset: Open Web Text

Neuron 277 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: 4.6042. Min Range: -4.6042

Max Act: 4.5714. Min Act: -0.1700

Data Index: 1373239 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 4.6042. Min Range: -4.6042

Max Act: 4.6042. Min Act: -0.1700

Data Index: 2213734 (Open Web Text)

Max Activating Token Index: 10

Text #2

Max Range: 4.6042. Min Range: -4.6042

Max Act: 4.5750. Min Act: -0.1700

Data Index: 5947984 (Open Web Text)

Max Activating Token Index: 9

Text #3

Max Range: 4.6042. Min Range: -4.6042

Max Act: 4.5434. Min Act: -0.1700

Data Index: 7192066 (Open Web Text)

Max Activating Token Index: 22

Text #4

Max Range: 4.6042. Min Range: -4.6042

Max Act: 4.5278. Min Act: -0.1700

Data Index: 6982165 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 4.6042. Min Range: -4.6042

Max Act: 4.5228. Min Act: -0.1700

Data Index: 8823731 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 4.6042. Min Range: -4.6042

Max Act: 4.5191. Min Act: -0.1700

Data Index: 4864486 (Open Web Text)

Max Activating Token Index: 30

Text #7

Max Range: 4.6042. Min Range: -4.6042

Max Act: 4.5192. Min Act: -0.1700

Data Index: 4474882 (Open Web Text)

Max Activating Token Index: 16

Text #8

Max Range: 4.6042. Min Range: -4.6042

Max Act: 4.5278. Min Act: -0.1700

Data Index: 886570 (Open Web Text)

Max Activating Token Index: 12

Text #9

Max Range: 4.6042. Min Range: -4.6042

Max Act: 4.5196. Min Act: -0.1700

Data Index: 4031773 (Open Web Text)

Max Activating Token Index: 48

Text #10

Max Range: 4.6042. Min Range: -4.6042

Max Act: 4.4911. Min Act: -0.1700

Data Index: 1921445 (Open Web Text)

Max Activating Token Index: 10

Text #11

Max Range: 4.6042. Min Range: -4.6042

Max Act: 4.4954. Min Act: -0.1700

Data Index: 4109699 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 4.6042. Min Range: -4.6042

Max Act: 4.5021. Min Act: -0.1700

Data Index: 8335301 (Open Web Text)

Max Activating Token Index: 346

Text #13

Max Range: 4.6042. Min Range: -4.6042

Max Act: 4.4968. Min Act: -0.1700

Data Index: 6761861 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 4.6042. Min Range: -4.6042

Max Act: 4.4641. Min Act: -0.1700

Data Index: 4999580 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 4.6042. Min Range: -4.6042

Max Act: 4.4507. Min Act: -0.1700

Data Index: 1139232 (Open Web Text)

Max Activating Token Index: 589

Text #16

Max Range: 4.6042. Min Range: -4.6042

Max Act: 4.4766. Min Act: -0.1700

Data Index: 567838 (Open Web Text)

Max Activating Token Index: 8

Text #17

Max Range: 4.6042. Min Range: -4.6042

Max Act: 4.4775. Min Act: -0.1700

Data Index: 850617 (Open Web Text)

Max Activating Token Index: 176

Text #18

Max Range: 4.6042. Min Range: -4.6042

Max Act: 4.4703. Min Act: -0.1700

Data Index: 6133859 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 4.6042. Min Range: -4.6042

Max Act: 4.4796. Min Act: -0.1700

Data Index: 4885723 (Open Web Text)

Max Activating Token Index: 18