Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3832 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1786. Min Range: -4.1786
Max Act: 4.1786. Min Act: -0.1700
Data Index: 3971257 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1786. Min Range: -4.1786
Max Act: 4.0536. Min Act: -0.1700
Data Index: 6035822 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1786. Min Range: -4.1786
Max Act: 4.0223. Min Act: -0.1700
Data Index: 2541060 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1786. Min Range: -4.1786
Max Act: 3.9285. Min Act: -0.1700
Data Index: 7031978 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1786. Min Range: -4.1786
Max Act: 3.9598. Min Act: -0.1700
Data Index: 3530830 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1786. Min Range: -4.1786
Max Act: 3.9285. Min Act: -0.1700
Data Index: 8158651 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1786. Min Range: -4.1786
Max Act: 3.8973. Min Act: -0.1700
Data Index: 4191585 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1786. Min Range: -4.1786
Max Act: 3.9285. Min Act: -0.1700
Data Index: 4678970 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1786. Min Range: -4.1786
Max Act: 3.8973. Min Act: -0.1700
Data Index: 2554225 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1786. Min Range: -4.1786
Max Act: 3.8973. Min Act: -0.1700
Data Index: 2356102 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1786. Min Range: -4.1786
Max Act: 3.8660. Min Act: -0.1700
Data Index: 4182740 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1786. Min Range: -4.1786
Max Act: 3.8660. Min Act: -0.1700
Data Index: 7171417 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1786. Min Range: -4.1786
Max Act: 3.8347. Min Act: -0.1700
Data Index: 8371886 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1786. Min Range: -4.1786
Max Act: 3.8347. Min Act: -0.1700
Data Index: 7242760 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1786. Min Range: -4.1786
Max Act: 3.8035. Min Act: -0.1700
Data Index: 2020828 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1786. Min Range: -4.1786
Max Act: 3.8347. Min Act: -0.1700
Data Index: 4327880 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1786. Min Range: -4.1786
Max Act: 3.8347. Min Act: -0.1700
Data Index: 8357277 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1786. Min Range: -4.1786
Max Act: 3.8347. Min Act: -0.1700
Data Index: 6423654 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1786. Min Range: -4.1786
Max Act: 3.8347. Min Act: -0.1700
Data Index: 1759826 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1786. Min Range: -4.1786
Max Act: 3.8347. Min Act: -0.1700
Data Index: 7468274 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #19