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

Dataset: Open Web Text

Neuron 578 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: 3.8176. Min Range: -3.8176

Max Act: 3.8176. Min Act: -0.1700

Data Index: 2864219 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 3.8176. Min Range: -3.8176

Max Act: 3.8077. Min Act: -0.1700

Data Index: 6952187 (Open Web Text)

Max Activating Token Index: 859

Text #2

Max Range: 3.8176. Min Range: -3.8176

Max Act: 3.7721. Min Act: -0.1700

Data Index: 1738790 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.8176. Min Range: -3.8176

Max Act: 3.7572. Min Act: -0.1700

Data Index: 300811 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.8176. Min Range: -3.8176

Max Act: 3.7438. Min Act: -0.1700

Data Index: 7341927 (Open Web Text)

Max Activating Token Index: 335

Text #5

Max Range: 3.8176. Min Range: -3.8176

Max Act: 3.7278. Min Act: -0.1700

Data Index: 3375274 (Open Web Text)

Max Activating Token Index: 749

Text #6

Max Range: 3.8176. Min Range: -3.8176

Max Act: 3.6819. Min Act: -0.1677

Data Index: 7249826 (Open Web Text)

Max Activating Token Index: 1006

Text #7

Max Range: 3.8176. Min Range: -3.8176

Max Act: 3.7033. Min Act: -0.1700

Data Index: 7128521 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 3.8176. Min Range: -3.8176

Max Act: 3.7157. Min Act: -0.1695

Data Index: 8560671 (Open Web Text)

Max Activating Token Index: 752

Text #9

Max Range: 3.8176. Min Range: -3.8176

Max Act: 3.7209. Min Act: -0.1700

Data Index: 3139370 (Open Web Text)

Max Activating Token Index: 386

Text #10

Max Range: 3.8176. Min Range: -3.8176

Max Act: 3.7058. Min Act: -0.1700

Data Index: 5935633 (Open Web Text)

Max Activating Token Index: 520

Text #11

Max Range: 3.8176. Min Range: -3.8176

Max Act: 3.6974. Min Act: -0.1697

Data Index: 7675023 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 3.8176. Min Range: -3.8176

Max Act: 3.6974. Min Act: -0.1700

Data Index: 7701282 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 3.8176. Min Range: -3.8176

Max Act: 3.6770. Min Act: -0.1700

Data Index: 6656546 (Open Web Text)

Max Activating Token Index: 906

Text #14

Max Range: 3.8176. Min Range: -3.8176

Max Act: 3.6958. Min Act: -0.1699

Data Index: 3279682 (Open Web Text)

Max Activating Token Index: 25

Text #15

Max Range: 3.8176. Min Range: -3.8176

Max Act: 3.6725. Min Act: -0.1697

Data Index: 2257963 (Open Web Text)

Max Activating Token Index: 746

Text #16

Max Range: 3.8176. Min Range: -3.8176

Max Act: 3.6614. Min Act: -0.1700

Data Index: 7944447 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.8176. Min Range: -3.8176

Max Act: 3.6614. Min Act: -0.1700

Data Index: 8135647 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.8176. Min Range: -3.8176

Max Act: 3.6496. Min Act: -0.1700

Data Index: 800121 (Open Web Text)

Max Activating Token Index: 11

Text #19

Max Range: 3.8176. Min Range: -3.8176

Max Act: 3.6617. Min Act: -0.1700

Data Index: 1211343 (Open Web Text)

Max Activating Token Index: 2