Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5351 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6011. Min Range: -2.6011
Max Act: 2.6011. Min Act: -0.1700
Data Index: 2229278 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6011. Min Range: -2.6011
Max Act: 2.5689. Min Act: -0.1700
Data Index: 3506025 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6011. Min Range: -2.6011
Max Act: 2.5043. Min Act: -0.1700
Data Index: 6286469 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6011. Min Range: -2.6011
Max Act: 2.4881. Min Act: -0.1700
Data Index: 319073 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6011. Min Range: -2.6011
Max Act: 2.4881. Min Act: -0.1700
Data Index: 6208676 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6011. Min Range: -2.6011
Max Act: 2.5043. Min Act: -0.1700
Data Index: 7665090 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6011. Min Range: -2.6011
Max Act: 2.4719. Min Act: -0.1700
Data Index: 3605708 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6011. Min Range: -2.6011
Max Act: 2.4719. Min Act: -0.1700
Data Index: 2612939 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6011. Min Range: -2.6011
Max Act: 2.4719. Min Act: -0.1700
Data Index: 1811190 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6011. Min Range: -2.6011
Max Act: 2.4393. Min Act: -0.1700
Data Index: 2188718 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6011. Min Range: -2.6011
Max Act: 2.4556. Min Act: -0.1700
Data Index: 652537 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6011. Min Range: -2.6011
Max Act: 2.4556. Min Act: -0.1700
Data Index: 1998907 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6011. Min Range: -2.6011
Max Act: 2.4556. Min Act: -0.1700
Data Index: 8323769 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6011. Min Range: -2.6011
Max Act: 2.4556. Min Act: -0.1700
Data Index: 5736038 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6011. Min Range: -2.6011
Max Act: 2.4556. Min Act: -0.1700
Data Index: 4974092 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6011. Min Range: -2.6011
Max Act: 2.4556. Min Act: -0.1700
Data Index: 5927769 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6011. Min Range: -2.6011
Max Act: 2.4556. Min Act: -0.1700
Data Index: 4361752 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6011. Min Range: -2.6011
Max Act: 2.4556. Min Act: -0.1700
Data Index: 829527 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6011. Min Range: -2.6011
Max Act: 2.4556. Min Act: -0.1700
Data Index: 653488 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6011. Min Range: -2.6011
Max Act: 2.4393. Min Act: -0.1700
Data Index: 2751287 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19