Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3537 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9169. Min Range: -6.9169
Max Act: 6.9169. Min Act: -0.1700
Data Index: 4039835 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9169. Min Range: -6.9169
Max Act: 6.8544. Min Act: -0.1700
Data Index: 145760 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9169. Min Range: -6.9169
Max Act: 6.7919. Min Act: -0.1700
Data Index: 8671022 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9169. Min Range: -6.9169
Max Act: 6.7607. Min Act: -0.1700
Data Index: 587529 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9169. Min Range: -6.9169
Max Act: 6.6357. Min Act: -0.1700
Data Index: 3760502 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9169. Min Range: -6.9169
Max Act: 6.5732. Min Act: -0.1700
Data Index: 5658517 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9169. Min Range: -6.9169
Max Act: 6.5107. Min Act: -0.1700
Data Index: 7674169 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9169. Min Range: -6.9169
Max Act: 6.5107. Min Act: -0.1700
Data Index: 7035170 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9169. Min Range: -6.9169
Max Act: 6.5107. Min Act: -0.1700
Data Index: 4943202 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9169. Min Range: -6.9169
Max Act: 6.5107. Min Act: -0.1700
Data Index: 6081050 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9169. Min Range: -6.9169
Max Act: 6.5107. Min Act: -0.1700
Data Index: 4039823 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9169. Min Range: -6.9169
Max Act: 6.4794. Min Act: -0.1700
Data Index: 7687006 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9169. Min Range: -6.9169
Max Act: 6.4169. Min Act: -0.1700
Data Index: 8057594 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9169. Min Range: -6.9169
Max Act: 6.4169. Min Act: -0.1700
Data Index: 7490046 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9169. Min Range: -6.9169
Max Act: 6.4482. Min Act: -0.1700
Data Index: 7227414 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9169. Min Range: -6.9169
Max Act: 6.4482. Min Act: -0.1700
Data Index: 4039820 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9169. Min Range: -6.9169
Max Act: 6.4482. Min Act: -0.1700
Data Index: 4503774 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9169. Min Range: -6.9169
Max Act: 6.4482. Min Act: -0.1700
Data Index: 7961425 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9169. Min Range: -6.9169
Max Act: 6.4169. Min Act: -0.1700
Data Index: 4095323 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9169. Min Range: -6.9169
Max Act: 6.4169. Min Act: -0.1700
Data Index: 2287800 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #19