Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3447 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7728. Min Range: -5.7728
Max Act: 5.7728. Min Act: -0.1700
Data Index: 5187381 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7728. Min Range: -5.7728
Max Act: 5.7103. Min Act: -0.1700
Data Index: 7410455 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7728. Min Range: -5.7728
Max Act: 5.7415. Min Act: -0.1700
Data Index: 1090980 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7728. Min Range: -5.7728
Max Act: 5.7103. Min Act: -0.1700
Data Index: 6988410 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7728. Min Range: -5.7728
Max Act: 5.6790. Min Act: -0.1700
Data Index: 8211689 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7728. Min Range: -5.7728
Max Act: 5.6165. Min Act: -0.1700
Data Index: 2885750 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7728. Min Range: -5.7728
Max Act: 5.6165. Min Act: -0.1700
Data Index: 3597076 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7728. Min Range: -5.7728
Max Act: 5.6165. Min Act: -0.1700
Data Index: 6593660 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7728. Min Range: -5.7728
Max Act: 5.6165. Min Act: -0.1700
Data Index: 6418567 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7728. Min Range: -5.7728
Max Act: 5.6165. Min Act: -0.1700
Data Index: 515254 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7728. Min Range: -5.7728
Max Act: 5.6165. Min Act: -0.1700
Data Index: 8560924 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7728. Min Range: -5.7728
Max Act: 5.5853. Min Act: -0.1700
Data Index: 6895495 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7728. Min Range: -5.7728
Max Act: 5.5853. Min Act: -0.1700
Data Index: 2156758 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7728. Min Range: -5.7728
Max Act: 5.5853. Min Act: -0.1700
Data Index: 5603720 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7728. Min Range: -5.7728
Max Act: 5.5853. Min Act: -0.1700
Data Index: 1384061 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7728. Min Range: -5.7728
Max Act: 5.5853. Min Act: -0.1700
Data Index: 5738070 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7728. Min Range: -5.7728
Max Act: 5.5853. Min Act: -0.1700
Data Index: 1152331 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7728. Min Range: -5.7728
Max Act: 5.5853. Min Act: -0.1700
Data Index: 97713 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7728. Min Range: -5.7728
Max Act: 5.5853. Min Act: -0.1700
Data Index: 3684182 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7728. Min Range: -5.7728
Max Act: 5.5853. Min Act: -0.1700
Data Index: 7631354 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #19