Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3926 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3923. Min Range: -9.3923
Max Act: 9.3923. Min Act: -0.1700
Data Index: 4712958 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3923. Min Range: -9.3923
Max Act: 8.7048. Min Act: -0.1700
Data Index: 248016 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3923. Min Range: -9.3923
Max Act: 8.6423. Min Act: -0.1700
Data Index: 7138398 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3923. Min Range: -9.3923
Max Act: 8.4548. Min Act: -0.1700
Data Index: 3886731 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3923. Min Range: -9.3923
Max Act: 8.3298. Min Act: -0.1700
Data Index: 1880885 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3923. Min Range: -9.3923
Max Act: 8.3298. Min Act: -0.1700
Data Index: 1507136 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3923. Min Range: -9.3923
Max Act: 8.2673. Min Act: -0.1700
Data Index: 248017 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3923. Min Range: -9.3923
Max Act: 8.2673. Min Act: -0.1700
Data Index: 1150659 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3923. Min Range: -9.3923
Max Act: 8.2673. Min Act: -0.1700
Data Index: 2404101 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3923. Min Range: -9.3923
Max Act: 8.2673. Min Act: -0.1700
Data Index: 5148604 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3923. Min Range: -9.3923
Max Act: 8.2048. Min Act: -0.1700
Data Index: 1463107 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3923. Min Range: -9.3923
Max Act: 8.2048. Min Act: -0.1700
Data Index: 3049006 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3923. Min Range: -9.3923
Max Act: 8.1423. Min Act: -0.1700
Data Index: 8602581 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3923. Min Range: -9.3923
Max Act: 8.1423. Min Act: -0.1700
Data Index: 248015 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3923. Min Range: -9.3923
Max Act: 8.1423. Min Act: -0.1700
Data Index: 6877401 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3923. Min Range: -9.3923
Max Act: 8.0798. Min Act: -0.1700
Data Index: 4361403 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3923. Min Range: -9.3923
Max Act: 8.0798. Min Act: -0.1700
Data Index: 8747700 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3923. Min Range: -9.3923
Max Act: 8.0798. Min Act: -0.1700
Data Index: 4380993 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3923. Min Range: -9.3923
Max Act: 8.0798. Min Act: -0.1700
Data Index: 2434261 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3923. Min Range: -9.3923
Max Act: 8.0173. Min Act: -0.1700
Data Index: 2786241 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #19