Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4458 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0550. Min Range: -6.0550
Max Act: 6.0550. Min Act: -0.1700
Data Index: 5666774 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0550. Min Range: -6.0550
Max Act: 5.8050. Min Act: -0.1700
Data Index: 6964270 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0550. Min Range: -6.0550
Max Act: 5.7425. Min Act: -0.1700
Data Index: 1671881 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0550. Min Range: -6.0550
Max Act: 5.7113. Min Act: -0.1700
Data Index: 6592800 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0550. Min Range: -6.0550
Max Act: 5.6800. Min Act: -0.1700
Data Index: 7333539 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0550. Min Range: -6.0550
Max Act: 5.6800. Min Act: -0.1700
Data Index: 388311 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0550. Min Range: -6.0550
Max Act: 5.6488. Min Act: -0.1700
Data Index: 5662863 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0550. Min Range: -6.0550
Max Act: 5.6488. Min Act: -0.1700
Data Index: 2171908 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0550. Min Range: -6.0550
Max Act: 5.6175. Min Act: -0.1700
Data Index: 1505127 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0550. Min Range: -6.0550
Max Act: 5.5863. Min Act: -0.1700
Data Index: 6643749 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0550. Min Range: -6.0550
Max Act: 5.6175. Min Act: -0.1700
Data Index: 3024546 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0550. Min Range: -6.0550
Max Act: 5.5550. Min Act: -0.1700
Data Index: 5457217 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0550. Min Range: -6.0550
Max Act: 5.5550. Min Act: -0.1700
Data Index: 2683439 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0550. Min Range: -6.0550
Max Act: 5.5550. Min Act: -0.1700
Data Index: 2275146 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0550. Min Range: -6.0550
Max Act: 5.5550. Min Act: -0.1700
Data Index: 2688565 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0550. Min Range: -6.0550
Max Act: 5.5550. Min Act: -0.1700
Data Index: 7792899 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0550. Min Range: -6.0550
Max Act: 5.5238. Min Act: -0.1700
Data Index: 2016752 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0550. Min Range: -6.0550
Max Act: 5.5238. Min Act: -0.1700
Data Index: 4590614 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0550. Min Range: -6.0550
Max Act: 5.5238. Min Act: -0.1700
Data Index: 8775174 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0550. Min Range: -6.0550
Max Act: 5.5238. Min Act: -0.1700
Data Index: 6920952 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19