Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 23 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.5506. Min Range: -9.5506
Max Act: 9.5506. Min Act: -0.1700
Data Index: 7903222 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5506. Min Range: -9.5506
Max Act: 9.4256. Min Act: -0.1700
Data Index: 7001930 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5506. Min Range: -9.5506
Max Act: 9.3631. Min Act: -0.1700
Data Index: 961673 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5506. Min Range: -9.5506
Max Act: 9.3631. Min Act: -0.1700
Data Index: 7001931 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5506. Min Range: -9.5506
Max Act: 9.3006. Min Act: -0.1700
Data Index: 4737995 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5506. Min Range: -9.5506
Max Act: 9.2381. Min Act: -0.1700
Data Index: 356004 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5506. Min Range: -9.5506
Max Act: 9.1131. Min Act: -0.1700
Data Index: 7001932 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5506. Min Range: -9.5506
Max Act: 9.0506. Min Act: -0.1700
Data Index: 6251957 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5506. Min Range: -9.5506
Max Act: 9.0506. Min Act: -0.1700
Data Index: 5580003 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5506. Min Range: -9.5506
Max Act: 8.9881. Min Act: -0.1700
Data Index: 7763743 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5506. Min Range: -9.5506
Max Act: 9.0506. Min Act: -0.1700
Data Index: 4483485 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5506. Min Range: -9.5506
Max Act: 8.9881. Min Act: -0.1700
Data Index: 333289 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5506. Min Range: -9.5506
Max Act: 8.8631. Min Act: -0.1700
Data Index: 4358796 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5506. Min Range: -9.5506
Max Act: 8.9881. Min Act: -0.1700
Data Index: 4069323 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5506. Min Range: -9.5506
Max Act: 8.8006. Min Act: -0.1700
Data Index: 2177294 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5506. Min Range: -9.5506
Max Act: 8.8631. Min Act: -0.1700
Data Index: 6798666 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5506. Min Range: -9.5506
Max Act: 8.8631. Min Act: -0.1700
Data Index: 6223221 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5506. Min Range: -9.5506
Max Act: 8.8631. Min Act: -0.1700
Data Index: 6133346 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5506. Min Range: -9.5506
Max Act: 8.8631. Min Act: -0.1700
Data Index: 948335 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5506. Min Range: -9.5506
Max Act: 8.8631. Min Act: -0.1700
Data Index: 776966 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #19