Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2077 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6097. Min Range: -7.6097
Max Act: 7.6097. Min Act: -0.1700
Data Index: 2266106 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6097. Min Range: -7.6097
Max Act: 7.5472. Min Act: -0.1700
Data Index: 6066673 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6097. Min Range: -7.6097
Max Act: 7.5472. Min Act: -0.1700
Data Index: 3694509 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6097. Min Range: -7.6097
Max Act: 7.4535. Min Act: -0.1700
Data Index: 1506821 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6097. Min Range: -7.6097
Max Act: 7.1722. Min Act: -0.1700
Data Index: 1075218 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6097. Min Range: -7.6097
Max Act: 7.1097. Min Act: -0.1700
Data Index: 3657342 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6097. Min Range: -7.6097
Max Act: 7.0785. Min Act: -0.1700
Data Index: 2591752 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6097. Min Range: -7.6097
Max Act: 7.0785. Min Act: -0.1700
Data Index: 4251674 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6097. Min Range: -7.6097
Max Act: 7.0472. Min Act: -0.1700
Data Index: 7072359 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6097. Min Range: -7.6097
Max Act: 7.0472. Min Act: -0.1700
Data Index: 3040542 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6097. Min Range: -7.6097
Max Act: 7.0160. Min Act: -0.1700
Data Index: 7677009 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6097. Min Range: -7.6097
Max Act: 7.0160. Min Act: -0.1700
Data Index: 4485014 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6097. Min Range: -7.6097
Max Act: 6.9847. Min Act: -0.1700
Data Index: 5986104 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6097. Min Range: -7.6097
Max Act: 6.9847. Min Act: -0.1700
Data Index: 8321466 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6097. Min Range: -7.6097
Max Act: 6.9222. Min Act: -0.1700
Data Index: 3092118 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6097. Min Range: -7.6097
Max Act: 6.9535. Min Act: -0.1700
Data Index: 5103389 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6097. Min Range: -7.6097
Max Act: 6.9535. Min Act: -0.1700
Data Index: 1001891 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6097. Min Range: -7.6097
Max Act: 6.9222. Min Act: -0.1700
Data Index: 4573132 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6097. Min Range: -7.6097
Max Act: 6.9222. Min Act: -0.1700
Data Index: 6739671 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6097. Min Range: -7.6097
Max Act: 6.8910. Min Act: -0.1700
Data Index: 1058945 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #19