Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3529 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4212. Min Range: -7.4212
Max Act: 7.4212. Min Act: -0.1700
Data Index: 6824658 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4212. Min Range: -7.4212
Max Act: 7.2337. Min Act: -0.1700
Data Index: 5764114 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4212. Min Range: -7.4212
Max Act: 7.2025. Min Act: -0.1700
Data Index: 3387242 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4212. Min Range: -7.4212
Max Act: 7.1087. Min Act: -0.1700
Data Index: 8532811 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4212. Min Range: -7.4212
Max Act: 7.0462. Min Act: -0.1700
Data Index: 7591059 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4212. Min Range: -7.4212
Max Act: 7.0462. Min Act: -0.1700
Data Index: 965434 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4212. Min Range: -7.4212
Max Act: 6.9837. Min Act: -0.1700
Data Index: 1485910 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4212. Min Range: -7.4212
Max Act: 6.9837. Min Act: -0.1700
Data Index: 7774837 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4212. Min Range: -7.4212
Max Act: 6.9837. Min Act: -0.1700
Data Index: 4203541 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4212. Min Range: -7.4212
Max Act: 6.9212. Min Act: -0.1700
Data Index: 5402674 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4212. Min Range: -7.4212
Max Act: 6.9525. Min Act: -0.1700
Data Index: 5381140 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4212. Min Range: -7.4212
Max Act: 6.9525. Min Act: -0.1700
Data Index: 1704112 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4212. Min Range: -7.4212
Max Act: 6.8900. Min Act: -0.1700
Data Index: 3076280 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4212. Min Range: -7.4212
Max Act: 6.9212. Min Act: -0.1700
Data Index: 6070429 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4212. Min Range: -7.4212
Max Act: 6.9212. Min Act: -0.1700
Data Index: 3871312 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4212. Min Range: -7.4212
Max Act: 6.9212. Min Act: -0.1700
Data Index: 1058382 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4212. Min Range: -7.4212
Max Act: 6.9212. Min Act: -0.1700
Data Index: 7501575 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4212. Min Range: -7.4212
Max Act: 6.8900. Min Act: -0.1700
Data Index: 3700588 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4212. Min Range: -7.4212
Max Act: 6.8587. Min Act: -0.1700
Data Index: 6772531 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4212. Min Range: -7.4212
Max Act: 6.8587. Min Act: -0.1700
Data Index: 1327832 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #19