Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2756 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0634. Min Range: -6.0634
Max Act: 6.0634. Min Act: -0.1700
Data Index: 6809315 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0634. Min Range: -6.0634
Max Act: 6.0322. Min Act: -0.1700
Data Index: 4775327 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0634. Min Range: -6.0634
Max Act: 6.0322. Min Act: -0.1700
Data Index: 5221661 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0634. Min Range: -6.0634
Max Act: 6.0009. Min Act: -0.1700
Data Index: 7163229 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0634. Min Range: -6.0634
Max Act: 6.0009. Min Act: -0.1700
Data Index: 2440364 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0634. Min Range: -6.0634
Max Act: 5.9697. Min Act: -0.1700
Data Index: 2790383 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0634. Min Range: -6.0634
Max Act: 5.9384. Min Act: -0.1700
Data Index: 1875719 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0634. Min Range: -6.0634
Max Act: 5.9384. Min Act: -0.1700
Data Index: 7674525 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0634. Min Range: -6.0634
Max Act: 5.9072. Min Act: -0.1700
Data Index: 4551666 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0634. Min Range: -6.0634
Max Act: 5.9072. Min Act: -0.1700
Data Index: 2256201 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0634. Min Range: -6.0634
Max Act: 5.9072. Min Act: -0.1700
Data Index: 8056676 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0634. Min Range: -6.0634
Max Act: 5.8759. Min Act: -0.1700
Data Index: 324196 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0634. Min Range: -6.0634
Max Act: 5.8759. Min Act: -0.1700
Data Index: 3260253 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0634. Min Range: -6.0634
Max Act: 5.8759. Min Act: -0.1698
Data Index: 7696677 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0634. Min Range: -6.0634
Max Act: 5.8759. Min Act: -0.1700
Data Index: 1717812 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0634. Min Range: -6.0634
Max Act: 5.8759. Min Act: -0.1700
Data Index: 1331720 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0634. Min Range: -6.0634
Max Act: 5.8759. Min Act: -0.1700
Data Index: 3924061 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0634. Min Range: -6.0634
Max Act: 5.8759. Min Act: -0.1700
Data Index: 8583809 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0634. Min Range: -6.0634
Max Act: 5.8447. Min Act: -0.1700
Data Index: 5329652 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0634. Min Range: -6.0634
Max Act: 5.8447. Min Act: -0.1700
Data Index: 2594972 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #19