Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3776 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1216. Min Range: -5.1216
Max Act: 5.1216. Min Act: -0.1700
Data Index: 2935806 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1216. Min Range: -5.1216
Max Act: 4.9966. Min Act: -0.1700
Data Index: 373819 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1216. Min Range: -5.1216
Max Act: 4.9341. Min Act: -0.1700
Data Index: 2136540 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1216. Min Range: -5.1216
Max Act: 4.9341. Min Act: -0.1700
Data Index: 57878 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1216. Min Range: -5.1216
Max Act: 4.9029. Min Act: -0.1700
Data Index: 6617097 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1216. Min Range: -5.1216
Max Act: 4.9029. Min Act: -0.1700
Data Index: 1485908 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1216. Min Range: -5.1216
Max Act: 4.9029. Min Act: -0.1700
Data Index: 1985120 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1216. Min Range: -5.1216
Max Act: 4.8716. Min Act: -0.1700
Data Index: 7588927 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1216. Min Range: -5.1216
Max Act: 4.8716. Min Act: -0.1700
Data Index: 2476639 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1216. Min Range: -5.1216
Max Act: 4.8404. Min Act: -0.1700
Data Index: 8372810 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1216. Min Range: -5.1216
Max Act: 4.8716. Min Act: -0.1700
Data Index: 57877 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1216. Min Range: -5.1216
Max Act: 4.8716. Min Act: -0.1700
Data Index: 1485909 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1216. Min Range: -5.1216
Max Act: 4.8404. Min Act: -0.1700
Data Index: 4930585 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1216. Min Range: -5.1216
Max Act: 4.8404. Min Act: -0.1700
Data Index: 696947 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1216. Min Range: -5.1216
Max Act: 4.8404. Min Act: -0.1700
Data Index: 373818 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1216. Min Range: -5.1216
Max Act: 4.8091. Min Act: -0.1700
Data Index: 412168 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1216. Min Range: -5.1216
Max Act: 4.8091. Min Act: -0.1700
Data Index: 3178971 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1216. Min Range: -5.1216
Max Act: 4.7779. Min Act: -0.1700
Data Index: 195166 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1216. Min Range: -5.1216
Max Act: 4.7779. Min Act: -0.1700
Data Index: 3042737 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1216. Min Range: -5.1216
Max Act: 4.7779. Min Act: -0.1700
Data Index: 604136 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #19