Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2086 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5265. Min Range: -6.5265
Max Act: 6.5265. Min Act: -0.1700
Data Index: 3560425 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5265. Min Range: -6.5265
Max Act: 6.4015. Min Act: -0.1700
Data Index: 6132738 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5265. Min Range: -6.5265
Max Act: 6.2140. Min Act: -0.1700
Data Index: 8647769 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5265. Min Range: -6.5265
Max Act: 6.1515. Min Act: -0.1700
Data Index: 728414 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5265. Min Range: -6.5265
Max Act: 6.0890. Min Act: -0.1700
Data Index: 5695322 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5265. Min Range: -6.5265
Max Act: 5.9015. Min Act: -0.1700
Data Index: 2181890 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5265. Min Range: -6.5265
Max Act: 5.9015. Min Act: -0.1700
Data Index: 1808547 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5265. Min Range: -6.5265
Max Act: 5.9015. Min Act: -0.1700
Data Index: 109103 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5265. Min Range: -6.5265
Max Act: 5.8077. Min Act: -0.1700
Data Index: 6473756 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5265. Min Range: -6.5265
Max Act: 5.8077. Min Act: -0.1700
Data Index: 8320591 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5265. Min Range: -6.5265
Max Act: 5.7765. Min Act: -0.1700
Data Index: 7532944 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5265. Min Range: -6.5265
Max Act: 5.7452. Min Act: -0.1700
Data Index: 439308 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5265. Min Range: -6.5265
Max Act: 5.7140. Min Act: -0.1700
Data Index: 7296514 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5265. Min Range: -6.5265
Max Act: 5.7452. Min Act: -0.1700
Data Index: 5628910 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5265. Min Range: -6.5265
Max Act: 5.7765. Min Act: -0.1700
Data Index: 3113603 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5265. Min Range: -6.5265
Max Act: 5.7452. Min Act: -0.1700
Data Index: 5435477 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5265. Min Range: -6.5265
Max Act: 5.6827. Min Act: -0.1700
Data Index: 6109825 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5265. Min Range: -6.5265
Max Act: 5.6827. Min Act: -0.1700
Data Index: 826481 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5265. Min Range: -6.5265
Max Act: 5.6515. Min Act: -0.1700
Data Index: 5623257 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5265. Min Range: -6.5265
Max Act: 5.6202. Min Act: -0.1700
Data Index: 2852811 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #19