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

Dataset: Open Web Text

Neuron 2533 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: 1.6825. Min Range: -1.6825

Max Act: 1.6825. Min Act: -0.1700

Data Index: 7328820 (Open Web Text)

Max Activating Token Index: 401

Text #1

Max Range: 1.6825. Min Range: -1.6825

Max Act: 1.5918. Min Act: -0.1688

Data Index: 5612936 (Open Web Text)

Max Activating Token Index: 777

Text #2

Max Range: 1.6825. Min Range: -1.6825

Max Act: 1.5851. Min Act: -0.1700

Data Index: 5708517 (Open Web Text)

Max Activating Token Index: 139

Text #3

Max Range: 1.6825. Min Range: -1.6825

Max Act: 1.5764. Min Act: -0.1699

Data Index: 4322661 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 1.6825. Min Range: -1.6825

Max Act: 1.5753. Min Act: -0.1700

Data Index: 7255275 (Open Web Text)

Max Activating Token Index: 102

Text #5

Max Range: 1.6825. Min Range: -1.6825

Max Act: 1.5749. Min Act: -0.1700

Data Index: 6777308 (Open Web Text)

Max Activating Token Index: 953

Text #6

Max Range: 1.6825. Min Range: -1.6825

Max Act: 1.5675. Min Act: -0.1700

Data Index: 3386484 (Open Web Text)

Max Activating Token Index: 753

Text #7

Max Range: 1.6825. Min Range: -1.6825

Max Act: 1.5598. Min Act: -0.1697

Data Index: 3724717 (Open Web Text)

Max Activating Token Index: 196

Text #8

Max Range: 1.6825. Min Range: -1.6825

Max Act: 1.5591. Min Act: -0.1700

Data Index: 843596 (Open Web Text)

Max Activating Token Index: 34

Text #9

Max Range: 1.6825. Min Range: -1.6825

Max Act: 1.5595. Min Act: -0.1700

Data Index: 2479113 (Open Web Text)

Max Activating Token Index: 38

Text #10

Max Range: 1.6825. Min Range: -1.6825

Max Act: 1.5530. Min Act: -0.1700

Data Index: 7691787 (Open Web Text)

Max Activating Token Index: 16

Text #11

Max Range: 1.6825. Min Range: -1.6825

Max Act: 1.5436. Min Act: -0.1700

Data Index: 6459075 (Open Web Text)

Max Activating Token Index: 14

Text #12

Max Range: 1.6825. Min Range: -1.6825

Max Act: 1.5444. Min Act: -0.1700

Data Index: 5844248 (Open Web Text)

Max Activating Token Index: 38

Text #13

Max Range: 1.6825. Min Range: -1.6825

Max Act: 1.5551. Min Act: -0.1700

Data Index: 8678487 (Open Web Text)

Max Activating Token Index: 137

Text #14

Max Range: 1.6825. Min Range: -1.6825

Max Act: 1.5568. Min Act: -0.1700

Data Index: 7163393 (Open Web Text)

Max Activating Token Index: 608

Text #15

Max Range: 1.6825. Min Range: -1.6825

Max Act: 1.5489. Min Act: -0.1700

Data Index: 4522543 (Open Web Text)

Max Activating Token Index: 26

Text #16

Max Range: 1.6825. Min Range: -1.6825

Max Act: 1.5405. Min Act: -0.1700

Data Index: 3455026 (Open Web Text)

Max Activating Token Index: 532

Text #17

Max Range: 1.6825. Min Range: -1.6825

Max Act: 1.5473. Min Act: -0.1700

Data Index: 905499 (Open Web Text)

Max Activating Token Index: 678

Text #18

Max Range: 1.6825. Min Range: -1.6825

Max Act: 1.5468. Min Act: -0.1700

Data Index: 3505567 (Open Web Text)

Max Activating Token Index: 64

Text #19

Max Range: 1.6825. Min Range: -1.6825

Max Act: 1.5478. Min Act: -0.1697

Data Index: 7577316 (Open Web Text)

Max Activating Token Index: 72