Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3674 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2555. Min Range: -7.2555
Max Act: 7.2555. Min Act: -0.1700
Data Index: 4814211 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2555. Min Range: -7.2555
Max Act: 6.9430. Min Act: -0.1700
Data Index: 5781644 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2555. Min Range: -7.2555
Max Act: 6.8492. Min Act: -0.1700
Data Index: 5194240 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2555. Min Range: -7.2555
Max Act: 6.8805. Min Act: -0.1700
Data Index: 6810388 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2555. Min Range: -7.2555
Max Act: 6.8180. Min Act: -0.1700
Data Index: 1000639 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2555. Min Range: -7.2555
Max Act: 6.6930. Min Act: -0.1700
Data Index: 3055096 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2555. Min Range: -7.2555
Max Act: 6.6930. Min Act: -0.1700
Data Index: 5552414 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2555. Min Range: -7.2555
Max Act: 6.6617. Min Act: -0.1700
Data Index: 5650891 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2555. Min Range: -7.2555
Max Act: 6.6617. Min Act: -0.1700
Data Index: 1851060 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2555. Min Range: -7.2555
Max Act: 6.6617. Min Act: -0.1700
Data Index: 4013149 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2555. Min Range: -7.2555
Max Act: 6.5992. Min Act: -0.1700
Data Index: 2564082 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2555. Min Range: -7.2555
Max Act: 6.5992. Min Act: -0.1700
Data Index: 4542429 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2555. Min Range: -7.2555
Max Act: 6.5992. Min Act: -0.1700
Data Index: 2792404 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2555. Min Range: -7.2555
Max Act: 6.5680. Min Act: -0.1700
Data Index: 1658576 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2555. Min Range: -7.2555
Max Act: 6.5992. Min Act: -0.1700
Data Index: 2991032 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2555. Min Range: -7.2555
Max Act: 6.5992. Min Act: -0.1700
Data Index: 2008750 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2555. Min Range: -7.2555
Max Act: 6.5680. Min Act: -0.1700
Data Index: 524320 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2555. Min Range: -7.2555
Max Act: 6.5680. Min Act: -0.1700
Data Index: 611665 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2555. Min Range: -7.2555
Max Act: 6.5367. Min Act: -0.1700
Data Index: 2877961 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2555. Min Range: -7.2555
Max Act: 6.5367. Min Act: -0.1700
Data Index: 1438079 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #19