Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3792 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8328. Min Range: -2.8328
Max Act: 2.8169. Min Act: -0.1700
Data Index: 2103773 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8328. Min Range: -2.8328
Max Act: 2.8010. Min Act: -0.1700
Data Index: 4302899 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8328. Min Range: -2.8328
Max Act: 2.8169. Min Act: -0.1700
Data Index: 4576325 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8328. Min Range: -2.8328
Max Act: 2.8328. Min Act: -0.1700
Data Index: 7253463 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8328. Min Range: -2.8328
Max Act: 2.7851. Min Act: -0.1700
Data Index: 1759607 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8328. Min Range: -2.8328
Max Act: 2.7851. Min Act: -0.1700
Data Index: 7281206 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8328. Min Range: -2.8328
Max Act: 2.7691. Min Act: -0.1700
Data Index: 700663 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8328. Min Range: -2.8328
Max Act: 2.7691. Min Act: -0.1700
Data Index: 5457272 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8328. Min Range: -2.8328
Max Act: 2.7532. Min Act: -0.1700
Data Index: 6422016 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8328. Min Range: -2.8328
Max Act: 2.7372. Min Act: -0.1700
Data Index: 5839928 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8328. Min Range: -2.8328
Max Act: 2.7372. Min Act: -0.1700
Data Index: 5234088 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8328. Min Range: -2.8328
Max Act: 2.7372. Min Act: -0.1700
Data Index: 8543878 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8328. Min Range: -2.8328
Max Act: 2.7372. Min Act: -0.1700
Data Index: 5317990 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8328. Min Range: -2.8328
Max Act: 2.7372. Min Act: -0.1700
Data Index: 648188 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8328. Min Range: -2.8328
Max Act: 2.7372. Min Act: -0.1700
Data Index: 1246142 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8328. Min Range: -2.8328
Max Act: 2.7372. Min Act: -0.1700
Data Index: 1538876 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8328. Min Range: -2.8328
Max Act: 2.7372. Min Act: -0.1700
Data Index: 7862807 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8328. Min Range: -2.8328
Max Act: 2.7212. Min Act: -0.1700
Data Index: 1409502 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8328. Min Range: -2.8328
Max Act: 2.7372. Min Act: -0.1700
Data Index: 6685923 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8328. Min Range: -2.8328
Max Act: 2.7212. Min Act: -0.1700
Data Index: 4299153 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #19