Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2596 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5052. Min Range: -6.5052
Max Act: 6.5052. Min Act: -0.1700
Data Index: 5702980 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5052. Min Range: -6.5052
Max Act: 6.4739. Min Act: -0.1700
Data Index: 7748429 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5052. Min Range: -6.5052
Max Act: 6.4739. Min Act: -0.1700
Data Index: 251053 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5052. Min Range: -6.5052
Max Act: 6.4739. Min Act: -0.1700
Data Index: 727624 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5052. Min Range: -6.5052
Max Act: 6.4114. Min Act: -0.1700
Data Index: 3676636 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5052. Min Range: -6.5052
Max Act: 6.4427. Min Act: -0.1700
Data Index: 2209856 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5052. Min Range: -6.5052
Max Act: 6.4114. Min Act: -0.1700
Data Index: 1905139 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5052. Min Range: -6.5052
Max Act: 6.4114. Min Act: -0.1700
Data Index: 1035161 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5052. Min Range: -6.5052
Max Act: 6.4114. Min Act: -0.1700
Data Index: 7379911 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5052. Min Range: -6.5052
Max Act: 6.4114. Min Act: -0.1700
Data Index: 6459761 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5052. Min Range: -6.5052
Max Act: 6.4114. Min Act: -0.1700
Data Index: 3125275 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5052. Min Range: -6.5052
Max Act: 6.3802. Min Act: -0.1700
Data Index: 5695562 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5052. Min Range: -6.5052
Max Act: 6.4114. Min Act: -0.1700
Data Index: 851868 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5052. Min Range: -6.5052
Max Act: 6.4114. Min Act: -0.1700
Data Index: 2729236 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5052. Min Range: -6.5052
Max Act: 6.4114. Min Act: -0.1700
Data Index: 4344299 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5052. Min Range: -6.5052
Max Act: 6.3802. Min Act: -0.1700
Data Index: 4342621 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5052. Min Range: -6.5052
Max Act: 6.4114. Min Act: -0.1700
Data Index: 3866492 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5052. Min Range: -6.5052
Max Act: 6.4427. Min Act: -0.1700
Data Index: 1871685 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5052. Min Range: -6.5052
Max Act: 6.3802. Min Act: -0.1700
Data Index: 1062675 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5052. Min Range: -6.5052
Max Act: 6.3802. Min Act: -0.1700
Data Index: 3802753 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #19