Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2103 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1595. Min Range: -7.1595
Max Act: 7.1595. Min Act: -0.1700
Data Index: 6564359 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1595. Min Range: -7.1595
Max Act: 7.1595. Min Act: -0.1700
Data Index: 864104 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1595. Min Range: -7.1595
Max Act: 7.0345. Min Act: -0.1700
Data Index: 4646538 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1595. Min Range: -7.1595
Max Act: 7.0033. Min Act: -0.1700
Data Index: 5950080 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1595. Min Range: -7.1595
Max Act: 6.9095. Min Act: -0.1700
Data Index: 4500371 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1595. Min Range: -7.1595
Max Act: 6.8783. Min Act: -0.1700
Data Index: 901787 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1595. Min Range: -7.1595
Max Act: 6.8783. Min Act: -0.1700
Data Index: 39002 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1595. Min Range: -7.1595
Max Act: 6.8158. Min Act: -0.1700
Data Index: 5211224 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1595. Min Range: -7.1595
Max Act: 6.7533. Min Act: -0.1700
Data Index: 4558739 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1595. Min Range: -7.1595
Max Act: 6.7220. Min Act: -0.1700
Data Index: 7611296 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1595. Min Range: -7.1595
Max Act: 6.7220. Min Act: -0.1700
Data Index: 1161033 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1595. Min Range: -7.1595
Max Act: 6.7220. Min Act: -0.1700
Data Index: 4167236 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1595. Min Range: -7.1595
Max Act: 6.7220. Min Act: -0.1700
Data Index: 8181354 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1595. Min Range: -7.1595
Max Act: 6.6908. Min Act: -0.1700
Data Index: 5534408 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1595. Min Range: -7.1595
Max Act: 6.6908. Min Act: -0.1700
Data Index: 509919 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1595. Min Range: -7.1595
Max Act: 6.6595. Min Act: -0.1700
Data Index: 5158071 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1595. Min Range: -7.1595
Max Act: 6.6908. Min Act: -0.1700
Data Index: 2314137 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1595. Min Range: -7.1595
Max Act: 6.6908. Min Act: -0.1700
Data Index: 5726922 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1595. Min Range: -7.1595
Max Act: 6.6595. Min Act: -0.1700
Data Index: 3421799 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1595. Min Range: -7.1595
Max Act: 6.6595. Min Act: -0.1700
Data Index: 4801256 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #19