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

Dataset: Open Web Text

Neuron 212 in Layer 0

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: 4.3404. Min Range: -4.3404

Max Act: 4.3404. Min Act: -0.1700

Data Index: 4183387 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 4.3404. Min Range: -4.3404

Max Act: 4.3366. Min Act: -0.1700

Data Index: 3254779 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 4.3404. Min Range: -4.3404

Max Act: 4.2912. Min Act: -0.1700

Data Index: 2928113 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 4.3404. Min Range: -4.3404

Max Act: 4.1848. Min Act: -0.1700

Data Index: 7701724 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 4.3404. Min Range: -4.3404

Max Act: 4.1802. Min Act: -0.1700

Data Index: 1491145 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 4.3404. Min Range: -4.3404

Max Act: 4.1778. Min Act: -0.1700

Data Index: 3149837 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 4.3404. Min Range: -4.3404

Max Act: 4.1808. Min Act: -0.1700

Data Index: 7166388 (Open Web Text)

Max Activating Token Index: 9

Text #7

Max Range: 4.3404. Min Range: -4.3404

Max Act: 4.1960. Min Act: -0.1700

Data Index: 2628719 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 4.3404. Min Range: -4.3404

Max Act: 4.1637. Min Act: -0.1700

Data Index: 3768446 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 4.3404. Min Range: -4.3404

Max Act: 4.1601. Min Act: -0.1700

Data Index: 732369 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 4.3404. Min Range: -4.3404

Max Act: 4.1500. Min Act: -0.1700

Data Index: 5376780 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 4.3404. Min Range: -4.3404

Max Act: 4.1465. Min Act: -0.1700

Data Index: 3080593 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 4.3404. Min Range: -4.3404

Max Act: 4.1500. Min Act: -0.1700

Data Index: 433384 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 4.3404. Min Range: -4.3404

Max Act: 4.1310. Min Act: -0.1700

Data Index: 977798 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 4.3404. Min Range: -4.3404

Max Act: 4.1319. Min Act: -0.1700

Data Index: 2764926 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 4.3404. Min Range: -4.3404

Max Act: 4.0937. Min Act: -0.1700

Data Index: 5940598 (Open Web Text)

Max Activating Token Index: 9

Text #16

Max Range: 4.3404. Min Range: -4.3404

Max Act: 4.0902. Min Act: -0.1700

Data Index: 5194576 (Open Web Text)

Max Activating Token Index: 9

Text #17

Max Range: 4.3404. Min Range: -4.3404

Max Act: 4.0979. Min Act: -0.1700

Data Index: 2407247 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 4.3404. Min Range: -4.3404

Max Act: 4.0934. Min Act: -0.1700

Data Index: 3724913 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 4.3404. Min Range: -4.3404

Max Act: 4.0930. Min Act: -0.1700

Data Index: 3738823 (Open Web Text)

Max Activating Token Index: 10