Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6150 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2590. Min Range: -5.2590
Max Act: 5.2590. Min Act: -0.1700
Data Index: 686465 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2590. Min Range: -5.2590
Max Act: 5.1340. Min Act: -0.1700
Data Index: 5769887 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2590. Min Range: -5.2590
Max Act: 5.1028. Min Act: -0.1700
Data Index: 7281698 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2590. Min Range: -5.2590
Max Act: 5.0090. Min Act: -0.1700
Data Index: 7336637 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2590. Min Range: -5.2590
Max Act: 4.9778. Min Act: -0.1700
Data Index: 3236260 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2590. Min Range: -5.2590
Max Act: 4.9778. Min Act: -0.1700
Data Index: 3188430 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2590. Min Range: -5.2590
Max Act: 5.0090. Min Act: -0.1700
Data Index: 404041 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2590. Min Range: -5.2590
Max Act: 4.9778. Min Act: -0.1700
Data Index: 4183239 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2590. Min Range: -5.2590
Max Act: 4.9778. Min Act: -0.1700
Data Index: 2186390 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2590. Min Range: -5.2590
Max Act: 4.9465. Min Act: -0.1700
Data Index: 4401322 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2590. Min Range: -5.2590
Max Act: 4.9465. Min Act: -0.1700
Data Index: 5537143 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2590. Min Range: -5.2590
Max Act: 4.9465. Min Act: -0.1700
Data Index: 46576 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2590. Min Range: -5.2590
Max Act: 4.9153. Min Act: -0.1700
Data Index: 4401321 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2590. Min Range: -5.2590
Max Act: 4.8840. Min Act: -0.1700
Data Index: 3070059 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2590. Min Range: -5.2590
Max Act: 4.9153. Min Act: -0.1700
Data Index: 5249416 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2590. Min Range: -5.2590
Max Act: 4.9153. Min Act: -0.1700
Data Index: 7336635 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2590. Min Range: -5.2590
Max Act: 4.9153. Min Act: -0.1700
Data Index: 6828917 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2590. Min Range: -5.2590
Max Act: 4.8840. Min Act: -0.1700
Data Index: 6069081 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2590. Min Range: -5.2590
Max Act: 4.8840. Min Act: -0.1700
Data Index: 1325076 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2590. Min Range: -5.2590
Max Act: 4.8528. Min Act: -0.1700
Data Index: 1974690 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #19