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

Dataset: Open Web Text

Neuron 1016 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: 4.8323. Min Range: -4.8323

Max Act: 4.7978. Min Act: -0.1700

Data Index: 17482 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 4.8323. Min Range: -4.8323

Max Act: 4.8323. Min Act: -0.1700

Data Index: 147660 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 4.8323. Min Range: -4.8323

Max Act: 4.7852. Min Act: -0.1700

Data Index: 4088950 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 4.8323. Min Range: -4.8323

Max Act: 4.7189. Min Act: -0.1700

Data Index: 2531208 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 4.8323. Min Range: -4.8323

Max Act: 4.7003. Min Act: -0.1700

Data Index: 7145628 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 4.8323. Min Range: -4.8323

Max Act: 4.7132. Min Act: -0.1700

Data Index: 2057361 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 4.8323. Min Range: -4.8323

Max Act: 4.7085. Min Act: -0.1700

Data Index: 928942 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 4.8323. Min Range: -4.8323

Max Act: 4.6909. Min Act: -0.1700

Data Index: 6600589 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 4.8323. Min Range: -4.8323

Max Act: 4.6625. Min Act: -0.1700

Data Index: 1888222 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 4.8323. Min Range: -4.8323

Max Act: 4.6277. Min Act: -0.1700

Data Index: 809688 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 4.8323. Min Range: -4.8323

Max Act: 4.6659. Min Act: -0.1700

Data Index: 5550376 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 4.8323. Min Range: -4.8323

Max Act: 4.6260. Min Act: -0.1700

Data Index: 3887674 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 4.8323. Min Range: -4.8323

Max Act: 4.6328. Min Act: -0.1700

Data Index: 3916403 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 4.8323. Min Range: -4.8323

Max Act: 4.6297. Min Act: -0.1700

Data Index: 7066187 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 4.8323. Min Range: -4.8323

Max Act: 4.6058. Min Act: -0.1700

Data Index: 2084320 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 4.8323. Min Range: -4.8323

Max Act: 4.7083. Min Act: -0.1700

Data Index: 8052246 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 4.8323. Min Range: -4.8323

Max Act: 4.6286. Min Act: -0.1700

Data Index: 19730 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 4.8323. Min Range: -4.8323

Max Act: 4.6007. Min Act: -0.1700

Data Index: 4778289 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 4.8323. Min Range: -4.8323

Max Act: 4.5845. Min Act: -0.1700

Data Index: 5022060 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 4.8323. Min Range: -4.8323

Max Act: 4.5872. Min Act: -0.1700

Data Index: 6702860 (Open Web Text)

Max Activating Token Index: 1023