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

Dataset: Open Web Text

Neuron 2247 in Layer 6

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: 5.7824. Min Range: -5.7824

Max Act: 5.7316. Min Act: -0.1700

Data Index: 3958353 (Open Web Text)

Max Activating Token Index: 983

Text #1

Max Range: 5.7824. Min Range: -5.7824

Max Act: 5.7824. Min Act: -0.1700

Data Index: 2040043 (Open Web Text)

Max Activating Token Index: 526

Text #2

Max Range: 5.7824. Min Range: -5.7824

Max Act: 5.7159. Min Act: -0.1700

Data Index: 7743565 (Open Web Text)

Max Activating Token Index: 583

Text #3

Max Range: 5.7824. Min Range: -5.7824

Max Act: 5.6925. Min Act: -0.1700

Data Index: 1635120 (Open Web Text)

Max Activating Token Index: 881

Text #4

Max Range: 5.7824. Min Range: -5.7824

Max Act: 5.6677. Min Act: -0.1700

Data Index: 6844899 (Open Web Text)

Max Activating Token Index: 236

Text #5

Max Range: 5.7824. Min Range: -5.7824

Max Act: 5.6598. Min Act: -0.1700

Data Index: 2426505 (Open Web Text)

Max Activating Token Index: 773

Text #6

Max Range: 5.7824. Min Range: -5.7824

Max Act: 5.6163. Min Act: -0.1700

Data Index: 7955961 (Open Web Text)

Max Activating Token Index: 328

Text #7

Max Range: 5.7824. Min Range: -5.7824

Max Act: 5.5933. Min Act: -0.1700

Data Index: 2491172 (Open Web Text)

Max Activating Token Index: 655

Text #8

Max Range: 5.7824. Min Range: -5.7824

Max Act: 5.5972. Min Act: -0.1700

Data Index: 2925851 (Open Web Text)

Max Activating Token Index: 246

Text #9

Max Range: 5.7824. Min Range: -5.7824

Max Act: 5.5644. Min Act: -0.1700

Data Index: 5702356 (Open Web Text)

Max Activating Token Index: 689

Text #10

Max Range: 5.7824. Min Range: -5.7824

Max Act: 5.5947. Min Act: -0.1700

Data Index: 5088488 (Open Web Text)

Max Activating Token Index: 31

Text #11

Max Range: 5.7824. Min Range: -5.7824

Max Act: 5.5854. Min Act: -0.1700

Data Index: 6753055 (Open Web Text)

Max Activating Token Index: 44

Text #12

Max Range: 5.7824. Min Range: -5.7824

Max Act: 5.5914. Min Act: -0.1700

Data Index: 4404610 (Open Web Text)

Max Activating Token Index: 668

Text #13

Max Range: 5.7824. Min Range: -5.7824

Max Act: 5.5684. Min Act: -0.1700

Data Index: 2394073 (Open Web Text)

Max Activating Token Index: 627

Text #14

Max Range: 5.7824. Min Range: -5.7824

Max Act: 5.5298. Min Act: -0.1700

Data Index: 4701437 (Open Web Text)

Max Activating Token Index: 85

Text #15

Max Range: 5.7824. Min Range: -5.7824

Max Act: 5.5152. Min Act: -0.1700

Data Index: 1907010 (Open Web Text)

Max Activating Token Index: 372

Text #16

Max Range: 5.7824. Min Range: -5.7824

Max Act: 5.5085. Min Act: -0.1700

Data Index: 7625256 (Open Web Text)

Max Activating Token Index: 616

Text #17

Max Range: 5.7824. Min Range: -5.7824

Max Act: 5.6064. Min Act: -0.1700

Data Index: 5839696 (Open Web Text)

Max Activating Token Index: 451

Text #18

Max Range: 5.7824. Min Range: -5.7824

Max Act: 5.5511. Min Act: -0.1700

Data Index: 4653128 (Open Web Text)

Max Activating Token Index: 279

Text #19

Max Range: 5.7824. Min Range: -5.7824

Max Act: 5.5235. Min Act: -0.1700

Data Index: 2533209 (Open Web Text)

Max Activating Token Index: 401