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

Dataset: Open Web Text

Neuron 1793 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: 1.4666. Min Range: -1.4666

Max Act: 1.4666. Min Act: -0.1699

Data Index: 5673722 (Open Web Text)

Max Activating Token Index: 79

Text #1

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.3838. Min Act: -0.1700

Data Index: 7865674 (Open Web Text)

Max Activating Token Index: 912

Text #2

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.3469. Min Act: -0.1700

Data Index: 5860602 (Open Web Text)

Max Activating Token Index: 81

Text #3

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.3480. Min Act: -0.1700

Data Index: 5673721 (Open Web Text)

Max Activating Token Index: 678

Text #4

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.3037. Min Act: -0.1699

Data Index: 8223669 (Open Web Text)

Max Activating Token Index: 66

Text #5

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.2531. Min Act: -0.1700

Data Index: 6506728 (Open Web Text)

Max Activating Token Index: 72

Text #6

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.2534. Min Act: -0.1700

Data Index: 2785548 (Open Web Text)

Max Activating Token Index: 822

Text #7

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.2444. Min Act: -0.1676

Data Index: 121159 (Open Web Text)

Max Activating Token Index: 794

Text #8

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.2374. Min Act: -0.1697

Data Index: 7876028 (Open Web Text)

Max Activating Token Index: 100

Text #9

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.2353. Min Act: -0.1699

Data Index: 1008123 (Open Web Text)

Max Activating Token Index: 70

Text #10

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.2253. Min Act: -0.1700

Data Index: 4685561 (Open Web Text)

Max Activating Token Index: 843

Text #11

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.2241. Min Act: -0.1700

Data Index: 5447646 (Open Web Text)

Max Activating Token Index: 687

Text #12

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.2260. Min Act: -0.1694

Data Index: 7407921 (Open Web Text)

Max Activating Token Index: 85

Text #13

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.2324. Min Act: -0.1700

Data Index: 68383 (Open Web Text)

Max Activating Token Index: 843

Text #14

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.2272. Min Act: -0.1700

Data Index: 7003745 (Open Web Text)

Max Activating Token Index: 85

Text #15

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.2308. Min Act: -0.1700

Data Index: 2380848 (Open Web Text)

Max Activating Token Index: 91

Text #16

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.2220. Min Act: -0.1698

Data Index: 701041 (Open Web Text)

Max Activating Token Index: 81

Text #17

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.2220. Min Act: -0.1699

Data Index: 6577791 (Open Web Text)

Max Activating Token Index: 851

Text #18

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.2060. Min Act: -0.1684

Data Index: 4007208 (Open Web Text)

Max Activating Token Index: 76

Text #19

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.2150. Min Act: -0.1697

Data Index: 473044 (Open Web Text)

Max Activating Token Index: 109