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

Dataset: Open Web Text

Neuron 2763 in Layer 1

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: 1.7144. Min Range: -1.7144

Max Act: 1.7144. Min Act: -0.1700

Data Index: 1188419 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 1.7144. Min Range: -1.7144

Max Act: 1.6999. Min Act: -0.1700

Data Index: 444007 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 1.7144. Min Range: -1.7144

Max Act: 1.6926. Min Act: -0.1700

Data Index: 3503002 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 1.7144. Min Range: -1.7144

Max Act: 1.6637. Min Act: -0.1700

Data Index: 8052295 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 1.7144. Min Range: -1.7144

Max Act: 1.6612. Min Act: -0.1700

Data Index: 8741531 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 1.7144. Min Range: -1.7144

Max Act: 1.6310. Min Act: -0.1700

Data Index: 3533833 (Open Web Text)

Max Activating Token Index: 10

Text #6

Max Range: 1.7144. Min Range: -1.7144

Max Act: 1.6402. Min Act: -0.1700

Data Index: 1788060 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 1.7144. Min Range: -1.7144

Max Act: 1.6391. Min Act: -0.1700

Data Index: 8831120 (Open Web Text)

Max Activating Token Index: 10

Text #8

Max Range: 1.7144. Min Range: -1.7144

Max Act: 1.6332. Min Act: -0.1700

Data Index: 6263171 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 1.7144. Min Range: -1.7144

Max Act: 1.6276. Min Act: -0.1700

Data Index: 1742572 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 1.7144. Min Range: -1.7144

Max Act: 1.6274. Min Act: -0.1700

Data Index: 3888466 (Open Web Text)

Max Activating Token Index: 984

Text #11

Max Range: 1.7144. Min Range: -1.7144

Max Act: 1.6284. Min Act: -0.1700

Data Index: 6854660 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 1.7144. Min Range: -1.7144

Max Act: 1.6280. Min Act: -0.1700

Data Index: 2900595 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 1.7144. Min Range: -1.7144

Max Act: 1.6229. Min Act: -0.1700

Data Index: 7799811 (Open Web Text)

Max Activating Token Index: 9

Text #14

Max Range: 1.7144. Min Range: -1.7144

Max Act: 1.6238. Min Act: -0.1700

Data Index: 4875953 (Open Web Text)

Max Activating Token Index: 47

Text #15

Max Range: 1.7144. Min Range: -1.7144

Max Act: 1.6280. Min Act: -0.1700

Data Index: 8382240 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 1.7144. Min Range: -1.7144

Max Act: 1.6207. Min Act: -0.1700

Data Index: 1250844 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 1.7144. Min Range: -1.7144

Max Act: 1.6128. Min Act: -0.1700

Data Index: 4365241 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 1.7144. Min Range: -1.7144

Max Act: 1.6051. Min Act: -0.1700

Data Index: 6348888 (Open Web Text)

Max Activating Token Index: 22

Text #19

Max Range: 1.7144. Min Range: -1.7144

Max Act: 1.6060. Min Act: -0.1700

Data Index: 1977861 (Open Web Text)

Max Activating Token Index: 16