Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 9 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1752. Min Range: -7.1752
Max Act: 7.1752. Min Act: -0.1700
Data Index: 2316585 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1752. Min Range: -7.1752
Max Act: 7.1439. Min Act: -0.1700
Data Index: 7132578 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1752. Min Range: -7.1752
Max Act: 7.0502. Min Act: -0.1700
Data Index: 7729945 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1752. Min Range: -7.1752
Max Act: 7.0502. Min Act: -0.1700
Data Index: 1837388 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1752. Min Range: -7.1752
Max Act: 7.0189. Min Act: -0.1700
Data Index: 2134201 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1752. Min Range: -7.1752
Max Act: 6.9877. Min Act: -0.1700
Data Index: 4498582 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1752. Min Range: -7.1752
Max Act: 6.9564. Min Act: -0.1700
Data Index: 6198240 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1752. Min Range: -7.1752
Max Act: 6.9564. Min Act: -0.1700
Data Index: 960275 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1752. Min Range: -7.1752
Max Act: 6.8939. Min Act: -0.1700
Data Index: 7132577 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1752. Min Range: -7.1752
Max Act: 6.9252. Min Act: -0.1700
Data Index: 306126 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1752. Min Range: -7.1752
Max Act: 6.8002. Min Act: -0.1700
Data Index: 4253201 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1752. Min Range: -7.1752
Max Act: 6.7689. Min Act: -0.1700
Data Index: 5754430 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1752. Min Range: -7.1752
Max Act: 6.8002. Min Act: -0.1700
Data Index: 6968414 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1752. Min Range: -7.1752
Max Act: 6.7377. Min Act: -0.1700
Data Index: 7104442 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1752. Min Range: -7.1752
Max Act: 6.7377. Min Act: -0.1700
Data Index: 5362743 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1752. Min Range: -7.1752
Max Act: 6.7064. Min Act: -0.1700
Data Index: 4357263 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1752. Min Range: -7.1752
Max Act: 6.6752. Min Act: -0.1700
Data Index: 4107572 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1752. Min Range: -7.1752
Max Act: 6.6439. Min Act: -0.1700
Data Index: 4421270 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1752. Min Range: -7.1752
Max Act: 6.6439. Min Act: -0.1700
Data Index: 4177547 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1752. Min Range: -7.1752
Max Act: 6.6127. Min Act: -0.1700
Data Index: 3682361 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #19