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

Dataset: Open Web Text

Neuron 3067 in Layer 4

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: 4.2301. Min Range: -4.2301

Max Act: 4.2301. Min Act: -0.1700

Data Index: 4846205 (Open Web Text)

Max Activating Token Index: 280

Text #1

Max Range: 4.2301. Min Range: -4.2301

Max Act: 4.1300. Min Act: -0.1700

Data Index: 6226422 (Open Web Text)

Max Activating Token Index: 862

Text #2

Max Range: 4.2301. Min Range: -4.2301

Max Act: 4.2006. Min Act: -0.1700

Data Index: 5202815 (Open Web Text)

Max Activating Token Index: 450

Text #3

Max Range: 4.2301. Min Range: -4.2301

Max Act: 4.2254. Min Act: -0.1700

Data Index: 5202821 (Open Web Text)

Max Activating Token Index: 101

Text #4

Max Range: 4.2301. Min Range: -4.2301

Max Act: 4.1225. Min Act: -0.1700

Data Index: 827768 (Open Web Text)

Max Activating Token Index: 878

Text #5

Max Range: 4.2301. Min Range: -4.2301

Max Act: 4.1013. Min Act: -0.1700

Data Index: 763648 (Open Web Text)

Max Activating Token Index: 201

Text #6

Max Range: 4.2301. Min Range: -4.2301

Max Act: 4.1630. Min Act: -0.1700

Data Index: 2190320 (Open Web Text)

Max Activating Token Index: 607

Text #7

Max Range: 4.2301. Min Range: -4.2301

Max Act: 4.0991. Min Act: -0.1700

Data Index: 8552256 (Open Web Text)

Max Activating Token Index: 150

Text #8

Max Range: 4.2301. Min Range: -4.2301

Max Act: 4.1165. Min Act: -0.1700

Data Index: 2529608 (Open Web Text)

Max Activating Token Index: 324

Text #9

Max Range: 4.2301. Min Range: -4.2301

Max Act: 4.1112. Min Act: -0.1700

Data Index: 2363172 (Open Web Text)

Max Activating Token Index: 889

Text #10

Max Range: 4.2301. Min Range: -4.2301

Max Act: 4.1023. Min Act: -0.1700

Data Index: 36554 (Open Web Text)

Max Activating Token Index: 700

Text #11

Max Range: 4.2301. Min Range: -4.2301

Max Act: 4.0193. Min Act: -0.1700

Data Index: 4084335 (Open Web Text)

Max Activating Token Index: 43

Text #12

Max Range: 4.2301. Min Range: -4.2301

Max Act: 4.0266. Min Act: -0.1700

Data Index: 5553377 (Open Web Text)

Max Activating Token Index: 72

Text #13

Max Range: 4.2301. Min Range: -4.2301

Max Act: 4.0049. Min Act: -0.1700

Data Index: 343195 (Open Web Text)

Max Activating Token Index: 22

Text #14

Max Range: 4.2301. Min Range: -4.2301

Max Act: 3.9546. Min Act: -0.1700

Data Index: 1472665 (Open Web Text)

Max Activating Token Index: 949

Text #15

Max Range: 4.2301. Min Range: -4.2301

Max Act: 3.9271. Min Act: -0.1700

Data Index: 5266351 (Open Web Text)

Max Activating Token Index: 878

Text #16

Max Range: 4.2301. Min Range: -4.2301

Max Act: 3.9480. Min Act: -0.1700

Data Index: 5211482 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 4.2301. Min Range: -4.2301

Max Act: 3.9885. Min Act: -0.1700

Data Index: 8501902 (Open Web Text)

Max Activating Token Index: 351

Text #18

Max Range: 4.2301. Min Range: -4.2301

Max Act: 4.0127. Min Act: -0.1700

Data Index: 349922 (Open Web Text)

Max Activating Token Index: 992

Text #19

Max Range: 4.2301. Min Range: -4.2301

Max Act: 3.9591. Min Act: -0.1700

Data Index: 3964442 (Open Web Text)

Max Activating Token Index: 116