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

Dataset: Open Web Text

Neuron 739 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: 1.4341. Min Range: -1.4341

Max Act: 1.4341. Min Act: -0.1659

Data Index: 3780885 (Open Web Text)

Max Activating Token Index: 10

Text #1

Max Range: 1.4341. Min Range: -1.4341

Max Act: 1.4206. Min Act: -0.1687

Data Index: 8634750 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 1.4341. Min Range: -1.4341

Max Act: 1.3888. Min Act: -0.1687

Data Index: 831160 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 1.4341. Min Range: -1.4341

Max Act: 1.3772. Min Act: -0.1508

Data Index: 2274132 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 1.4341. Min Range: -1.4341

Max Act: 1.3395. Min Act: -0.1518

Data Index: 7992535 (Open Web Text)

Max Activating Token Index: 35

Text #5

Max Range: 1.4341. Min Range: -1.4341

Max Act: 1.3332. Min Act: -0.1552

Data Index: 7232501 (Open Web Text)

Max Activating Token Index: 12

Text #6

Max Range: 1.4341. Min Range: -1.4341

Max Act: 1.3231. Min Act: -0.1407

Data Index: 653115 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 1.4341. Min Range: -1.4341

Max Act: 1.3143. Min Act: -0.1572

Data Index: 4859579 (Open Web Text)

Max Activating Token Index: 12

Text #8

Max Range: 1.4341. Min Range: -1.4341

Max Act: 1.3122. Min Act: -0.1651

Data Index: 2632595 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 1.4341. Min Range: -1.4341

Max Act: 1.3086. Min Act: -0.1590

Data Index: 4237148 (Open Web Text)

Max Activating Token Index: 12

Text #10

Max Range: 1.4341. Min Range: -1.4341

Max Act: 1.3043. Min Act: -0.1632

Data Index: 395689 (Open Web Text)

Max Activating Token Index: 10

Text #11

Max Range: 1.4341. Min Range: -1.4341

Max Act: 1.3003. Min Act: -0.1672

Data Index: 8099721 (Open Web Text)

Max Activating Token Index: 27

Text #12

Max Range: 1.4341. Min Range: -1.4341

Max Act: 1.2867. Min Act: -0.1648

Data Index: 7509830 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 1.4341. Min Range: -1.4341

Max Act: 1.2850. Min Act: -0.1508

Data Index: 8085132 (Open Web Text)

Max Activating Token Index: 81

Text #14

Max Range: 1.4341. Min Range: -1.4341

Max Act: 1.2792. Min Act: -0.1654

Data Index: 7813338 (Open Web Text)

Max Activating Token Index: 14

Text #15

Max Range: 1.4341. Min Range: -1.4341

Max Act: 1.2899. Min Act: -0.1439

Data Index: 5049430 (Open Web Text)

Max Activating Token Index: 10

Text #16

Max Range: 1.4341. Min Range: -1.4341

Max Act: 1.2885. Min Act: -0.1539

Data Index: 7667601 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 1.4341. Min Range: -1.4341

Max Act: 1.2932. Min Act: -0.1488

Data Index: 5343715 (Open Web Text)

Max Activating Token Index: 90

Text #18

Max Range: 1.4341. Min Range: -1.4341

Max Act: 1.2727. Min Act: -0.1695

Data Index: 4266881 (Open Web Text)

Max Activating Token Index: 171

Text #19

Max Range: 1.4341. Min Range: -1.4341

Max Act: 1.2751. Min Act: -0.1598

Data Index: 8204284 (Open Web Text)

Max Activating Token Index: 7