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

Dataset: Open Web Text

Neuron 1586 in Layer 1

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: 1.7093. Min Range: -1.7093

Max Act: 1.7039. Min Act: -0.1700

Data Index: 8713997 (Open Web Text)

Max Activating Token Index: 13

Text #1

Max Range: 1.7093. Min Range: -1.7093

Max Act: 1.7088. Min Act: -0.1700

Data Index: 7713829 (Open Web Text)

Max Activating Token Index: 12

Text #2

Max Range: 1.7093. Min Range: -1.7093

Max Act: 1.6981. Min Act: -0.1700

Data Index: 2934625 (Open Web Text)

Max Activating Token Index: 17

Text #3

Max Range: 1.7093. Min Range: -1.7093

Max Act: 1.7093. Min Act: -0.1700

Data Index: 7624595 (Open Web Text)

Max Activating Token Index: 64

Text #4

Max Range: 1.7093. Min Range: -1.7093

Max Act: 1.6919. Min Act: -0.1700

Data Index: 798889 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 1.7093. Min Range: -1.7093

Max Act: 1.6880. Min Act: -0.1700

Data Index: 1124220 (Open Web Text)

Max Activating Token Index: 13

Text #6

Max Range: 1.7093. Min Range: -1.7093

Max Act: 1.6813. Min Act: -0.1700

Data Index: 8210732 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 1.7093. Min Range: -1.7093

Max Act: 1.6861. Min Act: -0.1700

Data Index: 5756841 (Open Web Text)

Max Activating Token Index: 17

Text #8

Max Range: 1.7093. Min Range: -1.7093

Max Act: 1.6772. Min Act: -0.1700

Data Index: 5666419 (Open Web Text)

Max Activating Token Index: 34

Text #9

Max Range: 1.7093. Min Range: -1.7093

Max Act: 1.6720. Min Act: -0.1700

Data Index: 7313679 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 1.7093. Min Range: -1.7093

Max Act: 1.6654. Min Act: -0.1700

Data Index: 108794 (Open Web Text)

Max Activating Token Index: 11

Text #11

Max Range: 1.7093. Min Range: -1.7093

Max Act: 1.6656. Min Act: -0.1700

Data Index: 4653551 (Open Web Text)

Max Activating Token Index: 26

Text #12

Max Range: 1.7093. Min Range: -1.7093

Max Act: 1.6613. Min Act: -0.1700

Data Index: 3318623 (Open Web Text)

Max Activating Token Index: 538

Text #13

Max Range: 1.7093. Min Range: -1.7093

Max Act: 1.6546. Min Act: -0.1700

Data Index: 6578778 (Open Web Text)

Max Activating Token Index: 26

Text #14

Max Range: 1.7093. Min Range: -1.7093

Max Act: 1.6512. Min Act: -0.1700

Data Index: 7708919 (Open Web Text)

Max Activating Token Index: 13

Text #15

Max Range: 1.7093. Min Range: -1.7093

Max Act: 1.6548. Min Act: -0.1700

Data Index: 5854802 (Open Web Text)

Max Activating Token Index: 16

Text #16

Max Range: 1.7093. Min Range: -1.7093

Max Act: 1.6572. Min Act: -0.1700

Data Index: 6024973 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 1.7093. Min Range: -1.7093

Max Act: 1.6580. Min Act: -0.1700

Data Index: 6759073 (Open Web Text)

Max Activating Token Index: 13

Text #18

Max Range: 1.7093. Min Range: -1.7093

Max Act: 1.6502. Min Act: -0.1700

Data Index: 4118195 (Open Web Text)

Max Activating Token Index: 22

Text #19

Max Range: 1.7093. Min Range: -1.7093

Max Act: 1.6517. Min Act: -0.1700

Data Index: 4959204 (Open Web Text)

Max Activating Token Index: 34