Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 789 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2961. Min Range: -10.2961
Max Act: 10.2961. Min Act: -0.1700
Data Index: 6108466 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2961. Min Range: -10.2961
Max Act: 10.2336. Min Act: -0.1700
Data Index: 1395491 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2961. Min Range: -10.2961
Max Act: 10.1086. Min Act: -0.1700
Data Index: 4616825 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2961. Min Range: -10.2961
Max Act: 10.0461. Min Act: -0.1700
Data Index: 7978255 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2961. Min Range: -10.2961
Max Act: 9.9836. Min Act: -0.1700
Data Index: 2360768 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2961. Min Range: -10.2961
Max Act: 9.9211. Min Act: -0.1700
Data Index: 913649 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2961. Min Range: -10.2961
Max Act: 9.8586. Min Act: -0.1700
Data Index: 94258 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2961. Min Range: -10.2961
Max Act: 9.9211. Min Act: -0.1700
Data Index: 3716742 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2961. Min Range: -10.2961
Max Act: 9.9211. Min Act: -0.1700
Data Index: 1986991 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2961. Min Range: -10.2961
Max Act: 9.8586. Min Act: -0.1700
Data Index: 6986297 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2961. Min Range: -10.2961
Max Act: 9.7961. Min Act: -0.1700
Data Index: 1515976 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2961. Min Range: -10.2961
Max Act: 9.7961. Min Act: -0.1700
Data Index: 1678016 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2961. Min Range: -10.2961
Max Act: 9.7336. Min Act: -0.1700
Data Index: 5276905 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2961. Min Range: -10.2961
Max Act: 9.6711. Min Act: -0.1700
Data Index: 3890076 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2961. Min Range: -10.2961
Max Act: 9.5461. Min Act: -0.1700
Data Index: 4898268 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2961. Min Range: -10.2961
Max Act: 9.6086. Min Act: -0.1700
Data Index: 7553007 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2961. Min Range: -10.2961
Max Act: 9.5461. Min Act: -0.1700
Data Index: 5517330 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2961. Min Range: -10.2961
Max Act: 9.6086. Min Act: -0.1700
Data Index: 1709066 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2961. Min Range: -10.2961
Max Act: 9.6086. Min Act: -0.1700
Data Index: 3430301 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2961. Min Range: -10.2961
Max Act: 9.6086. Min Act: -0.1700
Data Index: 211372 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #19