Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3154 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5186. Min Range: -8.5186
Max Act: 8.5186. Min Act: -0.1700
Data Index: 6330883 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5186. Min Range: -8.5186
Max Act: 8.4561. Min Act: -0.1700
Data Index: 4232022 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5186. Min Range: -8.5186
Max Act: 8.2686. Min Act: -0.1700
Data Index: 8554915 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5186. Min Range: -8.5186
Max Act: 8.2061. Min Act: -0.1700
Data Index: 3884331 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5186. Min Range: -8.5186
Max Act: 8.2061. Min Act: -0.1700
Data Index: 3955917 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5186. Min Range: -8.5186
Max Act: 8.2061. Min Act: -0.1700
Data Index: 6743875 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5186. Min Range: -8.5186
Max Act: 8.2061. Min Act: -0.1700
Data Index: 8714598 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5186. Min Range: -8.5186
Max Act: 8.2061. Min Act: -0.1700
Data Index: 6942409 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5186. Min Range: -8.5186
Max Act: 8.1436. Min Act: -0.1700
Data Index: 7045600 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5186. Min Range: -8.5186
Max Act: 8.1436. Min Act: -0.1700
Data Index: 2432531 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5186. Min Range: -8.5186
Max Act: 8.0811. Min Act: -0.1700
Data Index: 1938615 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5186. Min Range: -8.5186
Max Act: 8.0811. Min Act: -0.1700
Data Index: 2924545 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5186. Min Range: -8.5186
Max Act: 8.0186. Min Act: -0.1700
Data Index: 2632471 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5186. Min Range: -8.5186
Max Act: 7.8936. Min Act: -0.1700
Data Index: 1234635 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5186. Min Range: -8.5186
Max Act: 7.8936. Min Act: -0.1700
Data Index: 3055840 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5186. Min Range: -8.5186
Max Act: 7.8936. Min Act: -0.1700
Data Index: 4585512 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5186. Min Range: -8.5186
Max Act: 7.8936. Min Act: -0.1700
Data Index: 550178 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5186. Min Range: -8.5186
Max Act: 7.8936. Min Act: -0.1700
Data Index: 7428644 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5186. Min Range: -8.5186
Max Act: 7.8311. Min Act: -0.1700
Data Index: 3857127 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5186. Min Range: -8.5186
Max Act: 7.8311. Min Act: -0.1700
Data Index: 7063543 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #19