Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3843 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4186. Min Range: -3.4186
Max Act: 3.4029. Min Act: -0.1700
Data Index: 6012401 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4186. Min Range: -3.4186
Max Act: 3.4029. Min Act: -0.1700
Data Index: 6758818 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4186. Min Range: -3.4186
Max Act: 3.3872. Min Act: -0.1700
Data Index: 2291160 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4186. Min Range: -3.4186
Max Act: 3.4029. Min Act: -0.1700
Data Index: 7249038 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4186. Min Range: -3.4186
Max Act: 3.3872. Min Act: -0.1700
Data Index: 4718369 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4186. Min Range: -3.4186
Max Act: 3.3872. Min Act: -0.1700
Data Index: 6415281 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4186. Min Range: -3.4186
Max Act: 3.3715. Min Act: -0.1700
Data Index: 5136902 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4186. Min Range: -3.4186
Max Act: 3.4186. Min Act: -0.1700
Data Index: 8295550 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4186. Min Range: -3.4186
Max Act: 3.3872. Min Act: -0.1700
Data Index: 3857932 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4186. Min Range: -3.4186
Max Act: 3.3558. Min Act: -0.1700
Data Index: 5377362 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4186. Min Range: -3.4186
Max Act: 3.3558. Min Act: -0.1700
Data Index: 5321605 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4186. Min Range: -3.4186
Max Act: 3.3245. Min Act: -0.1700
Data Index: 1391695 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4186. Min Range: -3.4186
Max Act: 3.3245. Min Act: -0.1700
Data Index: 7070802 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4186. Min Range: -3.4186
Max Act: 3.3401. Min Act: -0.1700
Data Index: 6067538 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4186. Min Range: -3.4186
Max Act: 3.3401. Min Act: -0.1700
Data Index: 8636697 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4186. Min Range: -3.4186
Max Act: 3.3401. Min Act: -0.1700
Data Index: 5690717 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4186. Min Range: -3.4186
Max Act: 3.3088. Min Act: -0.1700
Data Index: 6068609 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4186. Min Range: -3.4186
Max Act: 3.3245. Min Act: -0.1700
Data Index: 7029474 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4186. Min Range: -3.4186
Max Act: 3.2931. Min Act: -0.1700
Data Index: 2169767 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4186. Min Range: -3.4186
Max Act: 3.3245. Min Act: -0.1700
Data Index: 319030 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19