Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5995 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5649. Min Range: -3.5649
Max Act: 3.5649. Min Act: -0.1700
Data Index: 4769513 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5649. Min Range: -3.5649
Max Act: 3.4866. Min Act: -0.1700
Data Index: 7695356 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5649. Min Range: -3.5649
Max Act: 3.4396. Min Act: -0.1700
Data Index: 1518007 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5649. Min Range: -3.5649
Max Act: 3.4240. Min Act: -0.1700
Data Index: 8412604 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5649. Min Range: -3.5649
Max Act: 3.4240. Min Act: -0.1700
Data Index: 7284008 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5649. Min Range: -3.5649
Max Act: 3.4240. Min Act: -0.1700
Data Index: 6919625 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5649. Min Range: -3.5649
Max Act: 3.4083. Min Act: -0.1700
Data Index: 5107420 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5649. Min Range: -3.5649
Max Act: 3.4083. Min Act: -0.1700
Data Index: 7434886 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5649. Min Range: -3.5649
Max Act: 3.3926. Min Act: -0.1700
Data Index: 1134206 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5649. Min Range: -3.5649
Max Act: 3.3926. Min Act: -0.1700
Data Index: 3461982 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5649. Min Range: -3.5649
Max Act: 3.3769. Min Act: -0.1700
Data Index: 6516343 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5649. Min Range: -3.5649
Max Act: 3.3612. Min Act: -0.1700
Data Index: 8338196 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5649. Min Range: -3.5649
Max Act: 3.3456. Min Act: -0.1700
Data Index: 5041466 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5649. Min Range: -3.5649
Max Act: 3.3299. Min Act: -0.1700
Data Index: 4772980 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5649. Min Range: -3.5649
Max Act: 3.3612. Min Act: -0.1700
Data Index: 5840713 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5649. Min Range: -3.5649
Max Act: 3.3456. Min Act: -0.1700
Data Index: 8051063 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5649. Min Range: -3.5649
Max Act: 3.3456. Min Act: -0.1700
Data Index: 3115443 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5649. Min Range: -3.5649
Max Act: 3.3612. Min Act: -0.1700
Data Index: 2458449 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5649. Min Range: -3.5649
Max Act: 3.3612. Min Act: -0.1700
Data Index: 3447995 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5649. Min Range: -3.5649
Max Act: 3.3612. Min Act: -0.1700
Data Index: 654323 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #19