Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5384 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.7850. Min Range: -12.7850
Max Act: 12.7850. Min Act: -0.1700
Data Index: 6928001 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.7850. Min Range: -12.7850
Max Act: 12.5975. Min Act: -0.1700
Data Index: 4661076 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.7850. Min Range: -12.7850
Max Act: 12.4725. Min Act: -0.1700
Data Index: 6325413 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.7850. Min Range: -12.7850
Max Act: 12.4725. Min Act: -0.1700
Data Index: 8430073 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.7850. Min Range: -12.7850
Max Act: 12.4725. Min Act: -0.1700
Data Index: 5647458 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.7850. Min Range: -12.7850
Max Act: 12.4725. Min Act: -0.1700
Data Index: 1282118 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.7850. Min Range: -12.7850
Max Act: 12.4100. Min Act: -0.1700
Data Index: 5523251 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.7850. Min Range: -12.7850
Max Act: 12.4725. Min Act: -0.1700
Data Index: 283851 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.7850. Min Range: -12.7850
Max Act: 12.5350. Min Act: -0.1700
Data Index: 754679 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.7850. Min Range: -12.7850
Max Act: 12.4725. Min Act: -0.1700
Data Index: 6543992 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.7850. Min Range: -12.7850
Max Act: 12.4725. Min Act: -0.1700
Data Index: 7790544 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.7850. Min Range: -12.7850
Max Act: 12.4725. Min Act: -0.1700
Data Index: 687892 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.7850. Min Range: -12.7850
Max Act: 12.4100. Min Act: -0.1700
Data Index: 2734397 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.7850. Min Range: -12.7850
Max Act: 12.4100. Min Act: -0.1700
Data Index: 4299869 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.7850. Min Range: -12.7850
Max Act: 12.4100. Min Act: -0.1700
Data Index: 8021194 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.7850. Min Range: -12.7850
Max Act: 12.4100. Min Act: -0.1700
Data Index: 5297273 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.7850. Min Range: -12.7850
Max Act: 12.4100. Min Act: -0.1700
Data Index: 5667643 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.7850. Min Range: -12.7850
Max Act: 12.4100. Min Act: -0.1700
Data Index: 4937288 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.7850. Min Range: -12.7850
Max Act: 12.3475. Min Act: -0.1700
Data Index: 3533355 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.7850. Min Range: -12.7850
Max Act: 12.4100. Min Act: -0.1700
Data Index: 7103914 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #19