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

Dataset: Open Web Text

Neuron 3001 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: 6.0383. Min Range: -6.0383

Max Act: 6.0383. Min Act: -0.1700

Data Index: 7898147 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 6.0383. Min Range: -6.0383

Max Act: 5.9912. Min Act: -0.1700

Data Index: 8557001 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 6.0383. Min Range: -6.0383

Max Act: 6.0068. Min Act: -0.1700

Data Index: 235893 (Open Web Text)

Max Activating Token Index: 981

Text #3

Max Range: 6.0383. Min Range: -6.0383

Max Act: 5.9596. Min Act: -0.1700

Data Index: 1058799 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 6.0383. Min Range: -6.0383

Max Act: 5.9795. Min Act: -0.1700

Data Index: 6679149 (Open Web Text)

Max Activating Token Index: 21

Text #5

Max Range: 6.0383. Min Range: -6.0383

Max Act: 5.9478. Min Act: -0.1700

Data Index: 6750869 (Open Web Text)

Max Activating Token Index: 27

Text #6

Max Range: 6.0383. Min Range: -6.0383

Max Act: 5.9263. Min Act: -0.1700

Data Index: 6646403 (Open Web Text)

Max Activating Token Index: 19

Text #7

Max Range: 6.0383. Min Range: -6.0383

Max Act: 5.9321. Min Act: -0.1700

Data Index: 3973484 (Open Web Text)

Max Activating Token Index: 402

Text #8

Max Range: 6.0383. Min Range: -6.0383

Max Act: 5.9266. Min Act: -0.1700

Data Index: 8721312 (Open Web Text)

Max Activating Token Index: 540

Text #9

Max Range: 6.0383. Min Range: -6.0383

Max Act: 5.9069. Min Act: -0.1700

Data Index: 2288777 (Open Web Text)

Max Activating Token Index: 492

Text #10

Max Range: 6.0383. Min Range: -6.0383

Max Act: 5.9221. Min Act: -0.1700

Data Index: 2575426 (Open Web Text)

Max Activating Token Index: 28

Text #11

Max Range: 6.0383. Min Range: -6.0383

Max Act: 5.8894. Min Act: -0.1700

Data Index: 2741357 (Open Web Text)

Max Activating Token Index: 504

Text #12

Max Range: 6.0383. Min Range: -6.0383

Max Act: 5.8994. Min Act: -0.1700

Data Index: 7366571 (Open Web Text)

Max Activating Token Index: 20

Text #13

Max Range: 6.0383. Min Range: -6.0383

Max Act: 5.8984. Min Act: -0.1700

Data Index: 6631553 (Open Web Text)

Max Activating Token Index: 881

Text #14

Max Range: 6.0383. Min Range: -6.0383

Max Act: 5.9072. Min Act: -0.1700

Data Index: 4086876 (Open Web Text)

Max Activating Token Index: 9

Text #15

Max Range: 6.0383. Min Range: -6.0383

Max Act: 5.8919. Min Act: -0.1700

Data Index: 7749566 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 6.0383. Min Range: -6.0383

Max Act: 5.8999. Min Act: -0.1700

Data Index: 4436596 (Open Web Text)

Max Activating Token Index: 440

Text #17

Max Range: 6.0383. Min Range: -6.0383

Max Act: 5.8947. Min Act: -0.1700

Data Index: 6472987 (Open Web Text)

Max Activating Token Index: 570

Text #18

Max Range: 6.0383. Min Range: -6.0383

Max Act: 5.9079. Min Act: -0.1700

Data Index: 1134725 (Open Web Text)

Max Activating Token Index: 9

Text #19

Max Range: 6.0383. Min Range: -6.0383

Max Act: 5.9003. Min Act: -0.1700

Data Index: 7979218 (Open Web Text)

Max Activating Token Index: 34