Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 891 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7782. Min Range: -9.7782
Max Act: 9.7782. Min Act: -0.1700
Data Index: 409024 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7782. Min Range: -9.7782
Max Act: 9.6532. Min Act: -0.1700
Data Index: 6348486 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7782. Min Range: -9.7782
Max Act: 9.6532. Min Act: -0.1700
Data Index: 4176066 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7782. Min Range: -9.7782
Max Act: 9.5282. Min Act: -0.1700
Data Index: 765731 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7782. Min Range: -9.7782
Max Act: 9.5282. Min Act: -0.1700
Data Index: 560894 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7782. Min Range: -9.7782
Max Act: 9.5282. Min Act: -0.1700
Data Index: 1285829 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7782. Min Range: -9.7782
Max Act: 9.5282. Min Act: -0.1700
Data Index: 8552924 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7782. Min Range: -9.7782
Max Act: 9.4657. Min Act: -0.1700
Data Index: 8771105 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7782. Min Range: -9.7782
Max Act: 9.4657. Min Act: -0.1700
Data Index: 7031920 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7782. Min Range: -9.7782
Max Act: 9.4032. Min Act: -0.1700
Data Index: 6875103 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7782. Min Range: -9.7782
Max Act: 9.4032. Min Act: -0.1700
Data Index: 5722840 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7782. Min Range: -9.7782
Max Act: 9.4032. Min Act: -0.1700
Data Index: 445333 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7782. Min Range: -9.7782
Max Act: 9.4032. Min Act: -0.1700
Data Index: 918880 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7782. Min Range: -9.7782
Max Act: 9.3407. Min Act: -0.1700
Data Index: 7316383 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7782. Min Range: -9.7782
Max Act: 9.3407. Min Act: -0.1700
Data Index: 1084673 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7782. Min Range: -9.7782
Max Act: 9.3407. Min Act: -0.1700
Data Index: 5451766 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7782. Min Range: -9.7782
Max Act: 9.3407. Min Act: -0.1700
Data Index: 8498932 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7782. Min Range: -9.7782
Max Act: 9.3407. Min Act: -0.1700
Data Index: 968032 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7782. Min Range: -9.7782
Max Act: 9.3407. Min Act: -0.1700
Data Index: 2768581 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7782. Min Range: -9.7782
Max Act: 9.3407. Min Act: -0.1700
Data Index: 6900773 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19