Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5844 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6217. Min Range: -3.6217
Max Act: 3.6217. Min Act: -0.1700
Data Index: 4705530 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6217. Min Range: -3.6217
Max Act: 3.5904. Min Act: -0.1700
Data Index: 5630089 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6217. Min Range: -3.6217
Max Act: 3.5904. Min Act: -0.1700
Data Index: 827046 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6217. Min Range: -3.6217
Max Act: 3.5591. Min Act: -0.1700
Data Index: 4824082 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6217. Min Range: -3.6217
Max Act: 3.5591. Min Act: -0.1700
Data Index: 924922 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6217. Min Range: -3.6217
Max Act: 3.5591. Min Act: -0.1700
Data Index: 6986100 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6217. Min Range: -3.6217
Max Act: 3.5278. Min Act: -0.1700
Data Index: 1769737 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6217. Min Range: -3.6217
Max Act: 3.5278. Min Act: -0.1700
Data Index: 2050043 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6217. Min Range: -3.6217
Max Act: 3.5278. Min Act: -0.1700
Data Index: 8671810 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6217. Min Range: -3.6217
Max Act: 3.5278. Min Act: -0.1700
Data Index: 8295359 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6217. Min Range: -3.6217
Max Act: 3.5278. Min Act: -0.1700
Data Index: 8150514 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6217. Min Range: -3.6217
Max Act: 3.4965. Min Act: -0.1700
Data Index: 6750058 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6217. Min Range: -3.6217
Max Act: 3.4965. Min Act: -0.1700
Data Index: 2544945 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6217. Min Range: -3.6217
Max Act: 3.4965. Min Act: -0.1700
Data Index: 6924641 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6217. Min Range: -3.6217
Max Act: 3.4965. Min Act: -0.1700
Data Index: 3742374 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6217. Min Range: -3.6217
Max Act: 3.4965. Min Act: -0.1700
Data Index: 2005786 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6217. Min Range: -3.6217
Max Act: 3.4965. Min Act: -0.1700
Data Index: 5012473 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6217. Min Range: -3.6217
Max Act: 3.4965. Min Act: -0.1700
Data Index: 4844323 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6217. Min Range: -3.6217
Max Act: 3.4652. Min Act: -0.1700
Data Index: 920987 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6217. Min Range: -3.6217
Max Act: 3.4652. Min Act: -0.1700
Data Index: 420853 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19