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

Dataset: Open Web Text

Neuron 1007 in Layer 2

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: 3.6876. Min Range: -3.6876

Max Act: 3.6876. Min Act: -0.1700

Data Index: 7132964 (Open Web Text)

Max Activating Token Index: 622

Text #1

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.6284. Min Act: -0.1700

Data Index: 5058563 (Open Web Text)

Max Activating Token Index: 352

Text #2

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.6599. Min Act: -0.1700

Data Index: 7609345 (Open Web Text)

Max Activating Token Index: 251

Text #3

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.6295. Min Act: -0.1700

Data Index: 4345501 (Open Web Text)

Max Activating Token Index: 19

Text #4

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.6088. Min Act: -0.1700

Data Index: 1281730 (Open Web Text)

Max Activating Token Index: 144

Text #5

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.5994. Min Act: -0.1700

Data Index: 1356899 (Open Web Text)

Max Activating Token Index: 826

Text #6

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.6137. Min Act: -0.1700

Data Index: 7132962 (Open Web Text)

Max Activating Token Index: 709

Text #7

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.5828. Min Act: -0.1700

Data Index: 6204000 (Open Web Text)

Max Activating Token Index: 184

Text #8

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.5849. Min Act: -0.1700

Data Index: 4868254 (Open Web Text)

Max Activating Token Index: 70

Text #9

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.5790. Min Act: -0.1700

Data Index: 1145737 (Open Web Text)

Max Activating Token Index: 183

Text #10

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.5814. Min Act: -0.1700

Data Index: 8548160 (Open Web Text)

Max Activating Token Index: 510

Text #11

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.5655. Min Act: -0.1700

Data Index: 4195855 (Open Web Text)

Max Activating Token Index: 754

Text #12

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.5590. Min Act: -0.1700

Data Index: 3071371 (Open Web Text)

Max Activating Token Index: 85

Text #13

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.5531. Min Act: -0.1700

Data Index: 8140759 (Open Web Text)

Max Activating Token Index: 15

Text #14

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.5609. Min Act: -0.1700

Data Index: 6580560 (Open Web Text)

Max Activating Token Index: 337

Text #15

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.5448. Min Act: -0.1700

Data Index: 3585900 (Open Web Text)

Max Activating Token Index: 429

Text #16

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.4991. Min Act: -0.1700

Data Index: 785827 (Open Web Text)

Max Activating Token Index: 78

Text #17

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.5130. Min Act: -0.1700

Data Index: 2227430 (Open Web Text)

Max Activating Token Index: 308

Text #18

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.5360. Min Act: -0.1700

Data Index: 2587665 (Open Web Text)

Max Activating Token Index: 69

Text #19

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.5229. Min Act: -0.1700

Data Index: 3426452 (Open Web Text)

Max Activating Token Index: 721