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

Dataset: Open Web Text

Neuron 1076 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: 1.8825. Min Range: -1.8825

Max Act: 1.8825. Min Act: -0.1700

Data Index: 8097612 (Open Web Text)

Max Activating Token Index: 594

Text #1

Max Range: 1.8825. Min Range: -1.8825

Max Act: 1.7541. Min Act: -0.1700

Data Index: 5920394 (Open Web Text)

Max Activating Token Index: 378

Text #2

Max Range: 1.8825. Min Range: -1.8825

Max Act: 1.7384. Min Act: -0.1700

Data Index: 7279398 (Open Web Text)

Max Activating Token Index: 862

Text #3

Max Range: 1.8825. Min Range: -1.8825

Max Act: 1.7311. Min Act: -0.1700

Data Index: 8733975 (Open Web Text)

Max Activating Token Index: 261

Text #4

Max Range: 1.8825. Min Range: -1.8825

Max Act: 1.7308. Min Act: -0.1700

Data Index: 950639 (Open Web Text)

Max Activating Token Index: 207

Text #5

Max Range: 1.8825. Min Range: -1.8825

Max Act: 1.7131. Min Act: -0.1700

Data Index: 2192064 (Open Web Text)

Max Activating Token Index: 394

Text #6

Max Range: 1.8825. Min Range: -1.8825

Max Act: 1.6924. Min Act: -0.1700

Data Index: 2514776 (Open Web Text)

Max Activating Token Index: 550

Text #7

Max Range: 1.8825. Min Range: -1.8825

Max Act: 1.6820. Min Act: -0.1700

Data Index: 4829030 (Open Web Text)

Max Activating Token Index: 474

Text #8

Max Range: 1.8825. Min Range: -1.8825

Max Act: 1.6832. Min Act: -0.1700

Data Index: 2957668 (Open Web Text)

Max Activating Token Index: 356

Text #9

Max Range: 1.8825. Min Range: -1.8825

Max Act: 1.6764. Min Act: -0.1700

Data Index: 806035 (Open Web Text)

Max Activating Token Index: 529

Text #10

Max Range: 1.8825. Min Range: -1.8825

Max Act: 1.6732. Min Act: -0.1700

Data Index: 2073844 (Open Web Text)

Max Activating Token Index: 56

Text #11

Max Range: 1.8825. Min Range: -1.8825

Max Act: 1.6741. Min Act: -0.1700

Data Index: 7395396 (Open Web Text)

Max Activating Token Index: 550

Text #12

Max Range: 1.8825. Min Range: -1.8825

Max Act: 1.6693. Min Act: -0.1700

Data Index: 4162724 (Open Web Text)

Max Activating Token Index: 145

Text #13

Max Range: 1.8825. Min Range: -1.8825

Max Act: 1.6509. Min Act: -0.1700

Data Index: 6217527 (Open Web Text)

Max Activating Token Index: 873

Text #14

Max Range: 1.8825. Min Range: -1.8825

Max Act: 1.6563. Min Act: -0.1700

Data Index: 638133 (Open Web Text)

Max Activating Token Index: 225

Text #15

Max Range: 1.8825. Min Range: -1.8825

Max Act: 1.6584. Min Act: -0.1700

Data Index: 308169 (Open Web Text)

Max Activating Token Index: 356

Text #16

Max Range: 1.8825. Min Range: -1.8825

Max Act: 1.6569. Min Act: -0.1700

Data Index: 6068086 (Open Web Text)

Max Activating Token Index: 46

Text #17

Max Range: 1.8825. Min Range: -1.8825

Max Act: 1.6391. Min Act: -0.1700

Data Index: 1648003 (Open Web Text)

Max Activating Token Index: 639

Text #18

Max Range: 1.8825. Min Range: -1.8825

Max Act: 1.6480. Min Act: -0.1699

Data Index: 493585 (Open Web Text)

Max Activating Token Index: 572

Text #19

Max Range: 1.8825. Min Range: -1.8825

Max Act: 1.6497. Min Act: -0.1700

Data Index: 7348693 (Open Web Text)

Max Activating Token Index: 936