Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5144 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8752. Min Range: -6.8752
Max Act: 6.8752. Min Act: -0.1700
Data Index: 7038002 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8752. Min Range: -6.8752
Max Act: 6.5939. Min Act: -0.1700
Data Index: 5682630 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8752. Min Range: -6.8752
Max Act: 6.3127. Min Act: -0.1700
Data Index: 80014 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8752. Min Range: -6.8752
Max Act: 6.2502. Min Act: -0.1700
Data Index: 8633068 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8752. Min Range: -6.8752
Max Act: 6.1877. Min Act: -0.1700
Data Index: 6465815 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8752. Min Range: -6.8752
Max Act: 6.1252. Min Act: -0.1700
Data Index: 7070999 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8752. Min Range: -6.8752
Max Act: 6.0314. Min Act: -0.1700
Data Index: 447501 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8752. Min Range: -6.8752
Max Act: 6.0627. Min Act: -0.1700
Data Index: 5064802 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8752. Min Range: -6.8752
Max Act: 6.0002. Min Act: -0.1700
Data Index: 2404676 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8752. Min Range: -6.8752
Max Act: 6.0002. Min Act: -0.1700
Data Index: 6210334 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8752. Min Range: -6.8752
Max Act: 5.9689. Min Act: -0.1700
Data Index: 1499456 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8752. Min Range: -6.8752
Max Act: 5.9377. Min Act: -0.1700
Data Index: 2470054 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8752. Min Range: -6.8752
Max Act: 5.9377. Min Act: -0.1700
Data Index: 3451593 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8752. Min Range: -6.8752
Max Act: 5.8752. Min Act: -0.1700
Data Index: 1480527 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8752. Min Range: -6.8752
Max Act: 5.9064. Min Act: -0.1700
Data Index: 1245685 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8752. Min Range: -6.8752
Max Act: 5.9064. Min Act: -0.1700
Data Index: 637305 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8752. Min Range: -6.8752
Max Act: 5.8439. Min Act: -0.1700
Data Index: 2736674 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8752. Min Range: -6.8752
Max Act: 5.8752. Min Act: -0.1700
Data Index: 8593862 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8752. Min Range: -6.8752
Max Act: 5.8752. Min Act: -0.1700
Data Index: 6634498 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8752. Min Range: -6.8752
Max Act: 5.8439. Min Act: -0.1700
Data Index: 4564193 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #19