Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3193 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5775. Min Range: -7.5775
Max Act: 7.5775. Min Act: -0.1700
Data Index: 3651505 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5775. Min Range: -7.5775
Max Act: 7.5150. Min Act: -0.1700
Data Index: 2612339 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5775. Min Range: -7.5775
Max Act: 7.3587. Min Act: -0.1700
Data Index: 3502263 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5775. Min Range: -7.5775
Max Act: 7.3900. Min Act: -0.1700
Data Index: 777554 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5775. Min Range: -7.5775
Max Act: 7.3900. Min Act: -0.1700
Data Index: 604003 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5775. Min Range: -7.5775
Max Act: 7.3587. Min Act: -0.1700
Data Index: 1903254 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5775. Min Range: -7.5775
Max Act: 7.2962. Min Act: -0.1700
Data Index: 1903253 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5775. Min Range: -7.5775
Max Act: 7.2650. Min Act: -0.1700
Data Index: 177076 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5775. Min Range: -7.5775
Max Act: 7.2337. Min Act: -0.1700
Data Index: 8108362 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5775. Min Range: -7.5775
Max Act: 7.2337. Min Act: -0.1700
Data Index: 821845 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5775. Min Range: -7.5775
Max Act: 7.2337. Min Act: -0.1700
Data Index: 3194059 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5775. Min Range: -7.5775
Max Act: 7.2025. Min Act: -0.1700
Data Index: 547000 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5775. Min Range: -7.5775
Max Act: 7.1087. Min Act: -0.1700
Data Index: 1071352 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5775. Min Range: -7.5775
Max Act: 7.1400. Min Act: -0.1700
Data Index: 1922976 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5775. Min Range: -7.5775
Max Act: 7.1400. Min Act: -0.1700
Data Index: 2693435 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5775. Min Range: -7.5775
Max Act: 7.1087. Min Act: -0.1700
Data Index: 4430867 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5775. Min Range: -7.5775
Max Act: 7.1087. Min Act: -0.1700
Data Index: 4714295 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5775. Min Range: -7.5775
Max Act: 7.0775. Min Act: -0.1700
Data Index: 5200763 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5775. Min Range: -7.5775
Max Act: 7.0775. Min Act: -0.1700
Data Index: 7539870 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5775. Min Range: -7.5775
Max Act: 7.0775. Min Act: -0.1700
Data Index: 2333938 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #19