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

Dataset: Open Web Text

Neuron 2027 in Layer 2

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: 0.1392. Min Range: -0.1392

Max Act: 0.1392. Min Act: -0.1700

Data Index: 7091151 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1085. Min Act: -0.1692

Data Index: 2483819 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.0946. Min Act: -0.1700

Data Index: 8319222 (Open Web Text)

Max Activating Token Index: 987

Text #3

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.0904. Min Act: -0.1699

Data Index: 1862639 (Open Web Text)

Max Activating Token Index: 86

Text #4

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.0673. Min Act: -0.1700

Data Index: 5476066 (Open Web Text)

Max Activating Token Index: 846

Text #5

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.0720. Min Act: -0.1700

Data Index: 1277904 (Open Web Text)

Max Activating Token Index: 888

Text #6

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.0771. Min Act: -0.1699

Data Index: 3673776 (Open Web Text)

Max Activating Token Index: 931

Text #7

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.0680. Min Act: -0.1700

Data Index: 5863820 (Open Web Text)

Max Activating Token Index: 121

Text #8

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.0651. Min Act: -0.1697

Data Index: 643657 (Open Web Text)

Max Activating Token Index: 85

Text #9

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.0613. Min Act: -0.1668

Data Index: 8633699 (Open Web Text)

Max Activating Token Index: 51

Text #10

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.0646. Min Act: -0.1688

Data Index: 1618780 (Open Web Text)

Max Activating Token Index: 110

Text #11

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.0584. Min Act: -0.1674

Data Index: 2722861 (Open Web Text)

Max Activating Token Index: 76

Text #12

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.0585. Min Act: -0.1690

Data Index: 6447682 (Open Web Text)

Max Activating Token Index: 65

Text #13

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.0526. Min Act: -0.1698

Data Index: 4132961 (Open Web Text)

Max Activating Token Index: 79

Text #14

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.0544. Min Act: -0.1667

Data Index: 7790444 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.0556. Min Act: -0.1700

Data Index: 3552062 (Open Web Text)

Max Activating Token Index: 452

Text #16

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.0458. Min Act: -0.1699

Data Index: 1277025 (Open Web Text)

Max Activating Token Index: 818

Text #17

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.0482. Min Act: -0.1692

Data Index: 2139520 (Open Web Text)

Max Activating Token Index: 1007

Text #18

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.0441. Min Act: -0.1613

Data Index: 2257384 (Open Web Text)

Max Activating Token Index: 794

Text #19

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.0419. Min Act: -0.1674

Data Index: 8325390 (Open Web Text)

Max Activating Token Index: 1023