Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1919 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0178. Min Range: -6.0178
Max Act: 6.0178. Min Act: -0.1700
Data Index: 3856983 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0178. Min Range: -6.0178
Max Act: 5.8928. Min Act: -0.1700
Data Index: 6141367 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0178. Min Range: -6.0178
Max Act: 5.8616. Min Act: -0.1700
Data Index: 3294365 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0178. Min Range: -6.0178
Max Act: 5.7991. Min Act: -0.1700
Data Index: 5984895 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0178. Min Range: -6.0178
Max Act: 5.7678. Min Act: -0.1700
Data Index: 3033977 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0178. Min Range: -6.0178
Max Act: 5.7678. Min Act: -0.1700
Data Index: 7626854 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0178. Min Range: -6.0178
Max Act: 5.7678. Min Act: -0.1700
Data Index: 6113378 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0178. Min Range: -6.0178
Max Act: 5.7366. Min Act: -0.1700
Data Index: 3253834 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0178. Min Range: -6.0178
Max Act: 5.7053. Min Act: -0.1700
Data Index: 2313027 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0178. Min Range: -6.0178
Max Act: 5.6741. Min Act: -0.1700
Data Index: 5484993 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0178. Min Range: -6.0178
Max Act: 5.6116. Min Act: -0.1700
Data Index: 2071529 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0178. Min Range: -6.0178
Max Act: 5.6116. Min Act: -0.1700
Data Index: 4380135 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0178. Min Range: -6.0178
Max Act: 5.5803. Min Act: -0.1700
Data Index: 4874297 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0178. Min Range: -6.0178
Max Act: 5.5491. Min Act: -0.1700
Data Index: 4638688 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0178. Min Range: -6.0178
Max Act: 5.5178. Min Act: -0.1700
Data Index: 3426672 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0178. Min Range: -6.0178
Max Act: 5.5178. Min Act: -0.1700
Data Index: 6371919 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0178. Min Range: -6.0178
Max Act: 5.5491. Min Act: -0.1700
Data Index: 557153 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0178. Min Range: -6.0178
Max Act: 5.4866. Min Act: -0.1700
Data Index: 1418670 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0178. Min Range: -6.0178
Max Act: 5.5178. Min Act: -0.1700
Data Index: 1118227 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0178. Min Range: -6.0178
Max Act: 5.4866. Min Act: -0.1700
Data Index: 1398702 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #19