Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5058 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6562. Min Range: -6.6562
Max Act: 6.6562. Min Act: -0.1700
Data Index: 95935 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6562. Min Range: -6.6562
Max Act: 6.5624. Min Act: -0.1700
Data Index: 3345435 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6562. Min Range: -6.6562
Max Act: 6.2812. Min Act: -0.1700
Data Index: 6669436 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6562. Min Range: -6.6562
Max Act: 6.1874. Min Act: -0.1700
Data Index: 2774252 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6562. Min Range: -6.6562
Max Act: 6.1562. Min Act: -0.1700
Data Index: 6892981 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6562. Min Range: -6.6562
Max Act: 6.0624. Min Act: -0.1700
Data Index: 5521777 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6562. Min Range: -6.6562
Max Act: 6.0312. Min Act: -0.1700
Data Index: 7617420 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6562. Min Range: -6.6562
Max Act: 5.9999. Min Act: -0.1700
Data Index: 42798 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6562. Min Range: -6.6562
Max Act: 5.9999. Min Act: -0.1700
Data Index: 7087695 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6562. Min Range: -6.6562
Max Act: 5.9999. Min Act: -0.1700
Data Index: 4447264 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6562. Min Range: -6.6562
Max Act: 5.9687. Min Act: -0.1700
Data Index: 7518165 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6562. Min Range: -6.6562
Max Act: 5.9687. Min Act: -0.1700
Data Index: 5426886 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6562. Min Range: -6.6562
Max Act: 5.9687. Min Act: -0.1700
Data Index: 3683319 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6562. Min Range: -6.6562
Max Act: 5.9687. Min Act: -0.1700
Data Index: 931389 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6562. Min Range: -6.6562
Max Act: 5.9374. Min Act: -0.1700
Data Index: 5068879 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6562. Min Range: -6.6562
Max Act: 5.9687. Min Act: -0.1700
Data Index: 3114681 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6562. Min Range: -6.6562
Max Act: 5.9374. Min Act: -0.1700
Data Index: 3278458 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6562. Min Range: -6.6562
Max Act: 5.9062. Min Act: -0.1700
Data Index: 7650636 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6562. Min Range: -6.6562
Max Act: 5.9062. Min Act: -0.1700
Data Index: 3457241 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6562. Min Range: -6.6562
Max Act: 5.9062. Min Act: -0.1700
Data Index: 35178 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #19