Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5923 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6432. Min Range: -5.6432
Max Act: 5.6432. Min Act: -0.1700
Data Index: 3459220 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6432. Min Range: -5.6432
Max Act: 5.5495. Min Act: -0.1700
Data Index: 3204003 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6432. Min Range: -5.6432
Max Act: 5.4870. Min Act: -0.1700
Data Index: 165221 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6432. Min Range: -5.6432
Max Act: 5.4245. Min Act: -0.1700
Data Index: 165225 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6432. Min Range: -5.6432
Max Act: 5.2995. Min Act: -0.1700
Data Index: 4604219 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6432. Min Range: -5.6432
Max Act: 5.2995. Min Act: -0.1700
Data Index: 246827 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6432. Min Range: -5.6432
Max Act: 5.2682. Min Act: -0.1700
Data Index: 8502491 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6432. Min Range: -5.6432
Max Act: 5.2682. Min Act: -0.1700
Data Index: 5693070 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6432. Min Range: -5.6432
Max Act: 5.2370. Min Act: -0.1700
Data Index: 4490069 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6432. Min Range: -5.6432
Max Act: 5.2370. Min Act: -0.1700
Data Index: 802139 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6432. Min Range: -5.6432
Max Act: 5.2057. Min Act: -0.1700
Data Index: 6563953 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6432. Min Range: -5.6432
Max Act: 5.2370. Min Act: -0.1700
Data Index: 5708319 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6432. Min Range: -5.6432
Max Act: 5.2370. Min Act: -0.1700
Data Index: 1372082 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6432. Min Range: -5.6432
Max Act: 5.1432. Min Act: -0.1700
Data Index: 2401357 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6432. Min Range: -5.6432
Max Act: 5.1432. Min Act: -0.1700
Data Index: 7463062 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6432. Min Range: -5.6432
Max Act: 5.1432. Min Act: -0.1700
Data Index: 6507228 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6432. Min Range: -5.6432
Max Act: 5.0807. Min Act: -0.1700
Data Index: 802140 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6432. Min Range: -5.6432
Max Act: 5.0807. Min Act: -0.1700
Data Index: 1291044 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6432. Min Range: -5.6432
Max Act: 5.0807. Min Act: -0.1700
Data Index: 5178390 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6432. Min Range: -5.6432
Max Act: 5.0807. Min Act: -0.1700
Data Index: 5296385 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #19