Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5320 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0192. Min Range: -6.0192
Max Act: 6.0192. Min Act: -0.1700
Data Index: 7533803 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0192. Min Range: -6.0192
Max Act: 6.0192. Min Act: -0.1700
Data Index: 6059560 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0192. Min Range: -6.0192
Max Act: 6.0192. Min Act: -0.1700
Data Index: 2665621 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0192. Min Range: -6.0192
Max Act: 5.9567. Min Act: -0.1700
Data Index: 4327234 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0192. Min Range: -6.0192
Max Act: 5.9567. Min Act: -0.1700
Data Index: 702504 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0192. Min Range: -6.0192
Max Act: 5.9567. Min Act: -0.1700
Data Index: 4229595 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0192. Min Range: -6.0192
Max Act: 5.9255. Min Act: -0.1700
Data Index: 7306914 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0192. Min Range: -6.0192
Max Act: 5.8005. Min Act: -0.1700
Data Index: 4229580 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0192. Min Range: -6.0192
Max Act: 5.8005. Min Act: -0.1700
Data Index: 8258478 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0192. Min Range: -6.0192
Max Act: 5.7692. Min Act: -0.1700
Data Index: 798867 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0192. Min Range: -6.0192
Max Act: 5.8005. Min Act: -0.1700
Data Index: 3191331 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0192. Min Range: -6.0192
Max Act: 5.8005. Min Act: -0.1700
Data Index: 1825937 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0192. Min Range: -6.0192
Max Act: 5.8005. Min Act: -0.1700
Data Index: 5253645 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0192. Min Range: -6.0192
Max Act: 5.8005. Min Act: -0.1700
Data Index: 6380611 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0192. Min Range: -6.0192
Max Act: 5.8005. Min Act: -0.1700
Data Index: 3552369 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0192. Min Range: -6.0192
Max Act: 5.7380. Min Act: -0.1700
Data Index: 3514804 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0192. Min Range: -6.0192
Max Act: 5.7692. Min Act: -0.1700
Data Index: 5098444 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0192. Min Range: -6.0192
Max Act: 5.7692. Min Act: -0.1700
Data Index: 4327233 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0192. Min Range: -6.0192
Max Act: 5.7692. Min Act: -0.1700
Data Index: 6034626 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0192. Min Range: -6.0192
Max Act: 5.7380. Min Act: -0.1700
Data Index: 1922022 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #19