Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5392 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4104. Min Range: -5.4104
Max Act: 5.4104. Min Act: -0.1700
Data Index: 4489143 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4104. Min Range: -5.4104
Max Act: 5.2229. Min Act: -0.1700
Data Index: 659012 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4104. Min Range: -5.4104
Max Act: 5.1916. Min Act: -0.1700
Data Index: 5389331 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4104. Min Range: -5.4104
Max Act: 5.1916. Min Act: -0.1700
Data Index: 6630101 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4104. Min Range: -5.4104
Max Act: 5.1291. Min Act: -0.1700
Data Index: 6332462 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4104. Min Range: -5.4104
Max Act: 5.1604. Min Act: -0.1700
Data Index: 4951176 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4104. Min Range: -5.4104
Max Act: 5.1291. Min Act: -0.1700
Data Index: 8749192 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4104. Min Range: -5.4104
Max Act: 5.1604. Min Act: -0.1700
Data Index: 2301686 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4104. Min Range: -5.4104
Max Act: 5.1291. Min Act: -0.1700
Data Index: 1982126 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4104. Min Range: -5.4104
Max Act: 5.1291. Min Act: -0.1700
Data Index: 1757275 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4104. Min Range: -5.4104
Max Act: 5.1291. Min Act: -0.1700
Data Index: 6556554 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4104. Min Range: -5.4104
Max Act: 5.1291. Min Act: -0.1700
Data Index: 7669692 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4104. Min Range: -5.4104
Max Act: 5.1291. Min Act: -0.1700
Data Index: 5955129 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4104. Min Range: -5.4104
Max Act: 5.1291. Min Act: -0.1700
Data Index: 7029577 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4104. Min Range: -5.4104
Max Act: 5.0979. Min Act: -0.1700
Data Index: 3576213 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4104. Min Range: -5.4104
Max Act: 5.0979. Min Act: -0.1700
Data Index: 6119645 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4104. Min Range: -5.4104
Max Act: 5.0979. Min Act: -0.1700
Data Index: 6733312 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4104. Min Range: -5.4104
Max Act: 5.0979. Min Act: -0.1700
Data Index: 6607484 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4104. Min Range: -5.4104
Max Act: 5.0979. Min Act: -0.1700
Data Index: 4609295 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4104. Min Range: -5.4104
Max Act: 5.0979. Min Act: -0.1700
Data Index: 358666 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #19