Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3896 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8711. Min Range: -6.8711
Max Act: 6.8711. Min Act: -0.1700
Data Index: 7565465 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8711. Min Range: -6.8711
Max Act: 6.8399. Min Act: -0.1700
Data Index: 5230903 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8711. Min Range: -6.8711
Max Act: 6.7461. Min Act: -0.1700
Data Index: 3701784 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8711. Min Range: -6.8711
Max Act: 6.6836. Min Act: -0.1700
Data Index: 2445171 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8711. Min Range: -6.8711
Max Act: 6.7149. Min Act: -0.1700
Data Index: 8121546 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8711. Min Range: -6.8711
Max Act: 6.6524. Min Act: -0.1700
Data Index: 6800148 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8711. Min Range: -6.8711
Max Act: 6.6524. Min Act: -0.1700
Data Index: 8377830 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8711. Min Range: -6.8711
Max Act: 6.6524. Min Act: -0.1700
Data Index: 4341396 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8711. Min Range: -6.8711
Max Act: 6.6524. Min Act: -0.1700
Data Index: 2661715 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8711. Min Range: -6.8711
Max Act: 6.6211. Min Act: -0.1700
Data Index: 2981590 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8711. Min Range: -6.8711
Max Act: 6.5899. Min Act: -0.1700
Data Index: 154546 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8711. Min Range: -6.8711
Max Act: 6.5899. Min Act: -0.1700
Data Index: 3553736 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8711. Min Range: -6.8711
Max Act: 6.6524. Min Act: -0.1700
Data Index: 2223552 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8711. Min Range: -6.8711
Max Act: 6.6524. Min Act: -0.1700
Data Index: 4457114 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8711. Min Range: -6.8711
Max Act: 6.5899. Min Act: -0.1700
Data Index: 7557226 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8711. Min Range: -6.8711
Max Act: 6.6211. Min Act: -0.1700
Data Index: 2154846 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8711. Min Range: -6.8711
Max Act: 6.5899. Min Act: -0.1700
Data Index: 7426215 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8711. Min Range: -6.8711
Max Act: 6.5899. Min Act: -0.1700
Data Index: 5958819 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8711. Min Range: -6.8711
Max Act: 6.5899. Min Act: -0.1700
Data Index: 151125 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8711. Min Range: -6.8711
Max Act: 6.5899. Min Act: -0.1700
Data Index: 6663389 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19