Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3078 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4782. Min Range: -7.4782
Max Act: 7.4782. Min Act: -0.1700
Data Index: 1100558 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4782. Min Range: -7.4782
Max Act: 7.4470. Min Act: -0.1700
Data Index: 2716126 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4782. Min Range: -7.4782
Max Act: 7.3532. Min Act: -0.1700
Data Index: 3939937 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4782. Min Range: -7.4782
Max Act: 7.3532. Min Act: -0.1700
Data Index: 2475068 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4782. Min Range: -7.4782
Max Act: 7.1032. Min Act: -0.1700
Data Index: 6426979 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4782. Min Range: -7.4782
Max Act: 7.0407. Min Act: -0.1700
Data Index: 3421186 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4782. Min Range: -7.4782
Max Act: 7.0407. Min Act: -0.1700
Data Index: 970824 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4782. Min Range: -7.4782
Max Act: 6.9470. Min Act: -0.1700
Data Index: 4046856 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4782. Min Range: -7.4782
Max Act: 6.8845. Min Act: -0.1700
Data Index: 5583916 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4782. Min Range: -7.4782
Max Act: 6.8845. Min Act: -0.1700
Data Index: 6821121 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4782. Min Range: -7.4782
Max Act: 6.9157. Min Act: -0.1700
Data Index: 3623870 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4782. Min Range: -7.4782
Max Act: 6.9157. Min Act: -0.1700
Data Index: 3590819 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4782. Min Range: -7.4782
Max Act: 6.8532. Min Act: -0.1700
Data Index: 8013496 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4782. Min Range: -7.4782
Max Act: 6.8532. Min Act: -0.1700
Data Index: 7267689 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4782. Min Range: -7.4782
Max Act: 6.8220. Min Act: -0.1700
Data Index: 6903215 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4782. Min Range: -7.4782
Max Act: 6.8532. Min Act: -0.1700
Data Index: 1812276 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4782. Min Range: -7.4782
Max Act: 6.8532. Min Act: -0.1700
Data Index: 7708700 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4782. Min Range: -7.4782
Max Act: 6.8220. Min Act: -0.1700
Data Index: 1755764 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4782. Min Range: -7.4782
Max Act: 6.7907. Min Act: -0.1700
Data Index: 697470 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4782. Min Range: -7.4782
Max Act: 6.8220. Min Act: -0.1700
Data Index: 3891923 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #19