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

Dataset: Open Web Text

Neuron 2520 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: 3.2782. Min Range: -3.2782

Max Act: 3.2771. Min Act: -0.1700

Data Index: 8457324 (Open Web Text)

Max Activating Token Index: 153

Text #1

Max Range: 3.2782. Min Range: -3.2782

Max Act: 3.2782. Min Act: -0.1700

Data Index: 7573790 (Open Web Text)

Max Activating Token Index: 704

Text #2

Max Range: 3.2782. Min Range: -3.2782

Max Act: 3.2390. Min Act: -0.1700

Data Index: 3916746 (Open Web Text)

Max Activating Token Index: 203

Text #3

Max Range: 3.2782. Min Range: -3.2782

Max Act: 3.1888. Min Act: -0.1700

Data Index: 2561438 (Open Web Text)

Max Activating Token Index: 862

Text #4

Max Range: 3.2782. Min Range: -3.2782

Max Act: 3.2187. Min Act: -0.1700

Data Index: 4736883 (Open Web Text)

Max Activating Token Index: 686

Text #5

Max Range: 3.2782. Min Range: -3.2782

Max Act: 3.2094. Min Act: -0.1700

Data Index: 1856311 (Open Web Text)

Max Activating Token Index: 386

Text #6

Max Range: 3.2782. Min Range: -3.2782

Max Act: 3.1723. Min Act: -0.1700

Data Index: 6107909 (Open Web Text)

Max Activating Token Index: 229

Text #7

Max Range: 3.2782. Min Range: -3.2782

Max Act: 3.1949. Min Act: -0.1700

Data Index: 6435239 (Open Web Text)

Max Activating Token Index: 203

Text #8

Max Range: 3.2782. Min Range: -3.2782

Max Act: 3.1611. Min Act: -0.1700

Data Index: 6998277 (Open Web Text)

Max Activating Token Index: 143

Text #9

Max Range: 3.2782. Min Range: -3.2782

Max Act: 3.1834. Min Act: -0.1700

Data Index: 1358707 (Open Web Text)

Max Activating Token Index: 809

Text #10

Max Range: 3.2782. Min Range: -3.2782

Max Act: 3.1895. Min Act: -0.1700

Data Index: 2371624 (Open Web Text)

Max Activating Token Index: 237

Text #11

Max Range: 3.2782. Min Range: -3.2782

Max Act: 3.1552. Min Act: -0.1700

Data Index: 1908612 (Open Web Text)

Max Activating Token Index: 439

Text #12

Max Range: 3.2782. Min Range: -3.2782

Max Act: 3.1147. Min Act: -0.1700

Data Index: 1437776 (Open Web Text)

Max Activating Token Index: 858

Text #13

Max Range: 3.2782. Min Range: -3.2782

Max Act: 3.1609. Min Act: -0.1700

Data Index: 4348266 (Open Web Text)

Max Activating Token Index: 682

Text #14

Max Range: 3.2782. Min Range: -3.2782

Max Act: 3.1303. Min Act: -0.1700

Data Index: 4304699 (Open Web Text)

Max Activating Token Index: 213

Text #15

Max Range: 3.2782. Min Range: -3.2782

Max Act: 3.1744. Min Act: -0.1700

Data Index: 7497193 (Open Web Text)

Max Activating Token Index: 476

Text #16

Max Range: 3.2782. Min Range: -3.2782

Max Act: 3.0970. Min Act: -0.1700

Data Index: 2773434 (Open Web Text)

Max Activating Token Index: 829

Text #17

Max Range: 3.2782. Min Range: -3.2782

Max Act: 3.1440. Min Act: -0.1700

Data Index: 6730759 (Open Web Text)

Max Activating Token Index: 459

Text #18

Max Range: 3.2782. Min Range: -3.2782

Max Act: 3.1314. Min Act: -0.1700

Data Index: 2184030 (Open Web Text)

Max Activating Token Index: 386

Text #19

Max Range: 3.2782. Min Range: -3.2782

Max Act: 3.1451. Min Act: -0.1700

Data Index: 8571186 (Open Web Text)

Max Activating Token Index: 246