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

Dataset: Open Web Text

Neuron 1150 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: 1.3793. Min Range: -1.3793

Max Act: 1.3793. Min Act: -0.1694

Data Index: 5452748 (Open Web Text)

Max Activating Token Index: 61

Text #1

Max Range: 1.3793. Min Range: -1.3793

Max Act: 1.3316. Min Act: -0.1699

Data Index: 5365763 (Open Web Text)

Max Activating Token Index: 53

Text #2

Max Range: 1.3793. Min Range: -1.3793

Max Act: 1.3325. Min Act: -0.1697

Data Index: 4092486 (Open Web Text)

Max Activating Token Index: 135

Text #3

Max Range: 1.3793. Min Range: -1.3793

Max Act: 1.3077. Min Act: -0.1667

Data Index: 2012976 (Open Web Text)

Max Activating Token Index: 448

Text #4

Max Range: 1.3793. Min Range: -1.3793

Max Act: 1.3109. Min Act: -0.1700

Data Index: 5265207 (Open Web Text)

Max Activating Token Index: 39

Text #5

Max Range: 1.3793. Min Range: -1.3793

Max Act: 1.2817. Min Act: -0.1700

Data Index: 1526640 (Open Web Text)

Max Activating Token Index: 35

Text #6

Max Range: 1.3793. Min Range: -1.3793

Max Act: 1.2829. Min Act: -0.1691

Data Index: 6976585 (Open Web Text)

Max Activating Token Index: 375

Text #7

Max Range: 1.3793. Min Range: -1.3793

Max Act: 1.2718. Min Act: -0.1699

Data Index: 3870983 (Open Web Text)

Max Activating Token Index: 62

Text #8

Max Range: 1.3793. Min Range: -1.3793

Max Act: 1.2774. Min Act: -0.1690

Data Index: 1951132 (Open Web Text)

Max Activating Token Index: 344

Text #9

Max Range: 1.3793. Min Range: -1.3793

Max Act: 1.2785. Min Act: -0.1700

Data Index: 6386349 (Open Web Text)

Max Activating Token Index: 26

Text #10

Max Range: 1.3793. Min Range: -1.3793

Max Act: 1.2748. Min Act: -0.1665

Data Index: 6976575 (Open Web Text)

Max Activating Token Index: 570

Text #11

Max Range: 1.3793. Min Range: -1.3793

Max Act: 1.2698. Min Act: -0.1700

Data Index: 8709052 (Open Web Text)

Max Activating Token Index: 153

Text #12

Max Range: 1.3793. Min Range: -1.3793

Max Act: 1.2727. Min Act: -0.1700

Data Index: 3702311 (Open Web Text)

Max Activating Token Index: 81

Text #13

Max Range: 1.3793. Min Range: -1.3793

Max Act: 1.2688. Min Act: -0.1686

Data Index: 3346702 (Open Web Text)

Max Activating Token Index: 36

Text #14

Max Range: 1.3793. Min Range: -1.3793

Max Act: 1.2727. Min Act: -0.1700

Data Index: 8389865 (Open Web Text)

Max Activating Token Index: 427

Text #15

Max Range: 1.3793. Min Range: -1.3793

Max Act: 1.2722. Min Act: -0.1699

Data Index: 7217333 (Open Web Text)

Max Activating Token Index: 83

Text #16

Max Range: 1.3793. Min Range: -1.3793

Max Act: 1.2830. Min Act: -0.1697

Data Index: 4092488 (Open Web Text)

Max Activating Token Index: 506

Text #17

Max Range: 1.3793. Min Range: -1.3793

Max Act: 1.2674. Min Act: -0.1692

Data Index: 2116281 (Open Web Text)

Max Activating Token Index: 35

Text #18

Max Range: 1.3793. Min Range: -1.3793

Max Act: 1.2619. Min Act: -0.1700

Data Index: 831337 (Open Web Text)

Max Activating Token Index: 76

Text #19

Max Range: 1.3793. Min Range: -1.3793

Max Act: 1.2626. Min Act: -0.1690

Data Index: 3754101 (Open Web Text)

Max Activating Token Index: 338