Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3420 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1190. Min Range: -6.1190
Max Act: 6.1190. Min Act: -0.1700
Data Index: 8424985 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1190. Min Range: -6.1190
Max Act: 6.0565. Min Act: -0.1700
Data Index: 7300099 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1190. Min Range: -6.1190
Max Act: 6.0253. Min Act: -0.1700
Data Index: 5077639 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1190. Min Range: -6.1190
Max Act: 5.9628. Min Act: -0.1700
Data Index: 8559621 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1190. Min Range: -6.1190
Max Act: 5.9628. Min Act: -0.1700
Data Index: 8025076 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1190. Min Range: -6.1190
Max Act: 5.9628. Min Act: -0.1700
Data Index: 5568677 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1190. Min Range: -6.1190
Max Act: 5.9003. Min Act: -0.1700
Data Index: 8628827 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1190. Min Range: -6.1190
Max Act: 5.8690. Min Act: -0.1700
Data Index: 5805458 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1190. Min Range: -6.1190
Max Act: 5.8690. Min Act: -0.1700
Data Index: 4667087 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1190. Min Range: -6.1190
Max Act: 5.8690. Min Act: -0.1700
Data Index: 6442967 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1190. Min Range: -6.1190
Max Act: 5.8378. Min Act: -0.1700
Data Index: 6525942 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1190. Min Range: -6.1190
Max Act: 5.8378. Min Act: -0.1700
Data Index: 3496870 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1190. Min Range: -6.1190
Max Act: 5.8065. Min Act: -0.1700
Data Index: 6120913 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1190. Min Range: -6.1190
Max Act: 5.7753. Min Act: -0.1700
Data Index: 7089566 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1190. Min Range: -6.1190
Max Act: 5.7440. Min Act: -0.1700
Data Index: 8496050 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1190. Min Range: -6.1190
Max Act: 5.7440. Min Act: -0.1700
Data Index: 1168190 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1190. Min Range: -6.1190
Max Act: 5.7440. Min Act: -0.1700
Data Index: 6409591 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1190. Min Range: -6.1190
Max Act: 5.7128. Min Act: -0.1700
Data Index: 7024332 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1190. Min Range: -6.1190
Max Act: 5.7128. Min Act: -0.1700
Data Index: 2012360 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1190. Min Range: -6.1190
Max Act: 5.6815. Min Act: -0.1700
Data Index: 7599946 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #19