Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3344 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6556. Min Range: -6.6556
Max Act: 6.6556. Min Act: -0.1700
Data Index: 4719006 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6556. Min Range: -6.6556
Max Act: 6.3431. Min Act: -0.1700
Data Index: 749411 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6556. Min Range: -6.6556
Max Act: 6.3118. Min Act: -0.1700
Data Index: 2414851 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6556. Min Range: -6.6556
Max Act: 6.1556. Min Act: -0.1700
Data Index: 6935651 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6556. Min Range: -6.6556
Max Act: 6.1556. Min Act: -0.1700
Data Index: 8181022 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6556. Min Range: -6.6556
Max Act: 6.1243. Min Act: -0.1700
Data Index: 8591329 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6556. Min Range: -6.6556
Max Act: 6.1243. Min Act: -0.1700
Data Index: 5967807 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6556. Min Range: -6.6556
Max Act: 6.1243. Min Act: -0.1700
Data Index: 928145 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6556. Min Range: -6.6556
Max Act: 6.0931. Min Act: -0.1700
Data Index: 3308887 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6556. Min Range: -6.6556
Max Act: 6.0306. Min Act: -0.1700
Data Index: 2007762 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6556. Min Range: -6.6556
Max Act: 5.9993. Min Act: -0.1700
Data Index: 4840529 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6556. Min Range: -6.6556
Max Act: 5.9993. Min Act: -0.1700
Data Index: 8545137 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6556. Min Range: -6.6556
Max Act: 5.9681. Min Act: -0.1700
Data Index: 2230137 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6556. Min Range: -6.6556
Max Act: 5.8743. Min Act: -0.1700
Data Index: 6489434 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6556. Min Range: -6.6556
Max Act: 5.8743. Min Act: -0.1700
Data Index: 1365802 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6556. Min Range: -6.6556
Max Act: 5.8743. Min Act: -0.1700
Data Index: 8466636 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6556. Min Range: -6.6556
Max Act: 5.8743. Min Act: -0.1700
Data Index: 2690390 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6556. Min Range: -6.6556
Max Act: 5.8431. Min Act: -0.1700
Data Index: 8762543 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6556. Min Range: -6.6556
Max Act: 5.8118. Min Act: -0.1700
Data Index: 3849752 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6556. Min Range: -6.6556
Max Act: 5.7806. Min Act: -0.1700
Data Index: 5892753 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #19