Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2485 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.7053. Min Range: -10.7053
Max Act: 10.7053. Min Act: -0.1700
Data Index: 3447742 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.7053. Min Range: -10.7053
Max Act: 10.5803. Min Act: -0.1700
Data Index: 4180218 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.7053. Min Range: -10.7053
Max Act: 10.5178. Min Act: -0.1700
Data Index: 7958090 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.7053. Min Range: -10.7053
Max Act: 10.5178. Min Act: -0.1700
Data Index: 5553180 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.7053. Min Range: -10.7053
Max Act: 10.4553. Min Act: -0.1700
Data Index: 8784045 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.7053. Min Range: -10.7053
Max Act: 10.5178. Min Act: -0.1700
Data Index: 78623 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.7053. Min Range: -10.7053
Max Act: 10.4553. Min Act: -0.1700
Data Index: 7929104 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.7053. Min Range: -10.7053
Max Act: 10.4553. Min Act: -0.1700
Data Index: 8749227 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.7053. Min Range: -10.7053
Max Act: 10.4553. Min Act: -0.1700
Data Index: 945420 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.7053. Min Range: -10.7053
Max Act: 10.5178. Min Act: -0.1700
Data Index: 565297 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.7053. Min Range: -10.7053
Max Act: 10.3928. Min Act: -0.1700
Data Index: 704007 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.7053. Min Range: -10.7053
Max Act: 10.4553. Min Act: -0.1700
Data Index: 1921500 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.7053. Min Range: -10.7053
Max Act: 10.4553. Min Act: -0.1700
Data Index: 1675433 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.7053. Min Range: -10.7053
Max Act: 10.4553. Min Act: -0.1700
Data Index: 1905708 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.7053. Min Range: -10.7053
Max Act: 10.3928. Min Act: -0.1700
Data Index: 3015815 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.7053. Min Range: -10.7053
Max Act: 10.3928. Min Act: -0.1700
Data Index: 3914698 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.7053. Min Range: -10.7053
Max Act: 10.3928. Min Act: -0.1700
Data Index: 2205634 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.7053. Min Range: -10.7053
Max Act: 10.3928. Min Act: -0.1700
Data Index: 364730 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.7053. Min Range: -10.7053
Max Act: 10.3928. Min Act: -0.1700
Data Index: 2959215 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.7053. Min Range: -10.7053
Max Act: 10.3928. Min Act: -0.1700
Data Index: 3232961 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #19