Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1475 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.6015. Min Act: -0.1700
Data Index: 5267578 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.4140. Min Act: -0.1700
Data Index: 1426395 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.1952. Min Act: -0.1700
Data Index: 3106159 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.1015. Min Act: -0.1700
Data Index: 8293593 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.1015. Min Act: -0.1700
Data Index: 5638216 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.1015. Min Act: -0.1700
Data Index: 5866290 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.0702. Min Act: -0.1700
Data Index: 1881783 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.0390. Min Act: -0.1700
Data Index: 1552582 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.0390. Min Act: -0.1700
Data Index: 7460838 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.0077. Min Act: -0.1700
Data Index: 7925039 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6015. Min Range: -6.6015
Max Act: 5.9765. Min Act: -0.1700
Data Index: 3758233 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6015. Min Range: -6.6015
Max Act: 5.9765. Min Act: -0.1700
Data Index: 3510422 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6015. Min Range: -6.6015
Max Act: 5.9765. Min Act: -0.1700
Data Index: 3692136 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6015. Min Range: -6.6015
Max Act: 5.9452. Min Act: -0.1700
Data Index: 7634821 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6015. Min Range: -6.6015
Max Act: 5.9452. Min Act: -0.1700
Data Index: 3160732 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6015. Min Range: -6.6015
Max Act: 5.9452. Min Act: -0.1700
Data Index: 3846263 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6015. Min Range: -6.6015
Max Act: 5.9452. Min Act: -0.1700
Data Index: 1667614 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6015. Min Range: -6.6015
Max Act: 5.9452. Min Act: -0.1700
Data Index: 506719 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6015. Min Range: -6.6015
Max Act: 5.9452. Min Act: -0.1700
Data Index: 989588 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6015. Min Range: -6.6015
Max Act: 5.9140. Min Act: -0.1700
Data Index: 5194074 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #19