Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4462 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0845. Min Range: -9.0845
Max Act: 9.0845. Min Act: -0.1700
Data Index: 2260904 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0845. Min Range: -9.0845
Max Act: 8.9595. Min Act: -0.1700
Data Index: 8655980 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0845. Min Range: -9.0845
Max Act: 8.9595. Min Act: -0.1700
Data Index: 3320684 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0845. Min Range: -9.0845
Max Act: 8.7720. Min Act: -0.1700
Data Index: 7903895 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0845. Min Range: -9.0845
Max Act: 8.6470. Min Act: -0.1700
Data Index: 4676251 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0845. Min Range: -9.0845
Max Act: 8.7095. Min Act: -0.1700
Data Index: 4028521 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0845. Min Range: -9.0845
Max Act: 8.6470. Min Act: -0.1700
Data Index: 3856877 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0845. Min Range: -9.0845
Max Act: 8.5845. Min Act: -0.1700
Data Index: 5822474 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0845. Min Range: -9.0845
Max Act: 8.5220. Min Act: -0.1700
Data Index: 7380339 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0845. Min Range: -9.0845
Max Act: 8.5845. Min Act: -0.1700
Data Index: 6008030 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0845. Min Range: -9.0845
Max Act: 8.5845. Min Act: -0.1700
Data Index: 1039624 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0845. Min Range: -9.0845
Max Act: 8.5220. Min Act: -0.1700
Data Index: 4362812 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0845. Min Range: -9.0845
Max Act: 8.5220. Min Act: -0.1700
Data Index: 2791123 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0845. Min Range: -9.0845
Max Act: 8.5845. Min Act: -0.1700
Data Index: 7334631 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0845. Min Range: -9.0845
Max Act: 8.5220. Min Act: -0.1700
Data Index: 5758617 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0845. Min Range: -9.0845
Max Act: 8.5220. Min Act: -0.1700
Data Index: 6476877 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0845. Min Range: -9.0845
Max Act: 8.5220. Min Act: -0.1700
Data Index: 5540880 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0845. Min Range: -9.0845
Max Act: 8.5220. Min Act: -0.1700
Data Index: 6519109 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0845. Min Range: -9.0845
Max Act: 8.4595. Min Act: -0.1700
Data Index: 5978763 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0845. Min Range: -9.0845
Max Act: 8.4595. Min Act: -0.1700
Data Index: 1056367 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #19