Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3360 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.7935. Min Range: -1.7935
Max Act: 1.7935. Min Act: -0.1700
Data Index: 2642863 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7935. Min Range: -1.7935
Max Act: 1.7763. Min Act: -0.1700
Data Index: 7948669 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7935. Min Range: -1.7935
Max Act: 1.7590. Min Act: -0.1700
Data Index: 494633 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7935. Min Range: -1.7935
Max Act: 1.7763. Min Act: -0.1700
Data Index: 983032 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7935. Min Range: -1.7935
Max Act: 1.7590. Min Act: -0.1700
Data Index: 2129553 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7935. Min Range: -1.7935
Max Act: 1.7245. Min Act: -0.1700
Data Index: 8009720 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7935. Min Range: -1.7935
Max Act: 1.7245. Min Act: -0.1700
Data Index: 2189315 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7935. Min Range: -1.7935
Max Act: 1.7245. Min Act: -0.1700
Data Index: 7428706 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7935. Min Range: -1.7935
Max Act: 1.7245. Min Act: -0.1700
Data Index: 735870 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7935. Min Range: -1.7935
Max Act: 1.7245. Min Act: -0.1700
Data Index: 1012798 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7935. Min Range: -1.7935
Max Act: 1.7245. Min Act: -0.1700
Data Index: 2823102 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7935. Min Range: -1.7935
Max Act: 1.7071. Min Act: -0.1700
Data Index: 3002855 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7935. Min Range: -1.7935
Max Act: 1.7071. Min Act: -0.1700
Data Index: 6338562 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7935. Min Range: -1.7935
Max Act: 1.7071. Min Act: -0.1700
Data Index: 6503109 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7935. Min Range: -1.7935
Max Act: 1.7071. Min Act: -0.1700
Data Index: 6783770 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7935. Min Range: -1.7935
Max Act: 1.7071. Min Act: -0.1700
Data Index: 3501654 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7935. Min Range: -1.7935
Max Act: 1.7071. Min Act: -0.1700
Data Index: 6994046 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7935. Min Range: -1.7935
Max Act: 1.7071. Min Act: -0.1700
Data Index: 2136103 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7935. Min Range: -1.7935
Max Act: 1.7071. Min Act: -0.1700
Data Index: 2718944 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7935. Min Range: -1.7935
Max Act: 1.7071. Min Act: -0.1700
Data Index: 6166766 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #19