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

Dataset: Open Web Text

Neuron 71 in Layer 3

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: 4.1017. Min Range: -4.1017

Max Act: 4.0934. Min Act: -0.1700

Data Index: 5159494 (Open Web Text)

Max Activating Token Index: 134

Text #1

Max Range: 4.1017. Min Range: -4.1017

Max Act: 4.1017. Min Act: -0.1700

Data Index: 776480 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 4.1017. Min Range: -4.1017

Max Act: 4.0765. Min Act: -0.1700

Data Index: 3374349 (Open Web Text)

Max Activating Token Index: 751

Text #3

Max Range: 4.1017. Min Range: -4.1017

Max Act: 4.0784. Min Act: -0.1700

Data Index: 5029930 (Open Web Text)

Max Activating Token Index: 605

Text #4

Max Range: 4.1017. Min Range: -4.1017

Max Act: 4.0108. Min Act: -0.1700

Data Index: 4050416 (Open Web Text)

Max Activating Token Index: 950

Text #5

Max Range: 4.1017. Min Range: -4.1017

Max Act: 4.0972. Min Act: -0.1700

Data Index: 6611603 (Open Web Text)

Max Activating Token Index: 746

Text #6

Max Range: 4.1017. Min Range: -4.1017

Max Act: 4.0244. Min Act: -0.1700

Data Index: 8796783 (Open Web Text)

Max Activating Token Index: 483

Text #7

Max Range: 4.1017. Min Range: -4.1017

Max Act: 3.9846. Min Act: -0.1700

Data Index: 5973746 (Open Web Text)

Max Activating Token Index: 592

Text #8

Max Range: 4.1017. Min Range: -4.1017

Max Act: 4.0218. Min Act: -0.1700

Data Index: 4524253 (Open Web Text)

Max Activating Token Index: 523

Text #9

Max Range: 4.1017. Min Range: -4.1017

Max Act: 3.9807. Min Act: -0.1700

Data Index: 8666805 (Open Web Text)

Max Activating Token Index: 521

Text #10

Max Range: 4.1017. Min Range: -4.1017

Max Act: 3.9888. Min Act: -0.1700

Data Index: 3350198 (Open Web Text)

Max Activating Token Index: 557

Text #11

Max Range: 4.1017. Min Range: -4.1017

Max Act: 4.0035. Min Act: -0.1700

Data Index: 6293518 (Open Web Text)

Max Activating Token Index: 24

Text #12

Max Range: 4.1017. Min Range: -4.1017

Max Act: 3.9938. Min Act: -0.1700

Data Index: 6282771 (Open Web Text)

Max Activating Token Index: 412

Text #13

Max Range: 4.1017. Min Range: -4.1017

Max Act: 4.0397. Min Act: -0.1700

Data Index: 8739088 (Open Web Text)

Max Activating Token Index: 592

Text #14

Max Range: 4.1017. Min Range: -4.1017

Max Act: 3.9700. Min Act: -0.1700

Data Index: 2744606 (Open Web Text)

Max Activating Token Index: 50

Text #15

Max Range: 4.1017. Min Range: -4.1017

Max Act: 3.9524. Min Act: -0.1700

Data Index: 517361 (Open Web Text)

Max Activating Token Index: 86

Text #16

Max Range: 4.1017. Min Range: -4.1017

Max Act: 3.9644. Min Act: -0.1700

Data Index: 6553160 (Open Web Text)

Max Activating Token Index: 24

Text #17

Max Range: 4.1017. Min Range: -4.1017

Max Act: 3.9735. Min Act: -0.1700

Data Index: 1564586 (Open Web Text)

Max Activating Token Index: 727

Text #18

Max Range: 4.1017. Min Range: -4.1017

Max Act: 3.9577. Min Act: -0.1700

Data Index: 4627522 (Open Web Text)

Max Activating Token Index: 146

Text #19

Max Range: 4.1017. Min Range: -4.1017

Max Act: 3.9115. Min Act: -0.1700

Data Index: 8233686 (Open Web Text)

Max Activating Token Index: 853