Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5497 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4764. Min Range: -7.4764
Max Act: 7.4764. Min Act: -0.1700
Data Index: 7991792 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4764. Min Range: -7.4764
Max Act: 7.4139. Min Act: -0.1700
Data Index: 913039 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4764. Min Range: -7.4764
Max Act: 7.2577. Min Act: -0.1700
Data Index: 1568061 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4764. Min Range: -7.4764
Max Act: 7.1952. Min Act: -0.1700
Data Index: 5301973 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4764. Min Range: -7.4764
Max Act: 7.1639. Min Act: -0.1700
Data Index: 2436315 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4764. Min Range: -7.4764
Max Act: 7.1327. Min Act: -0.1700
Data Index: 1197501 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4764. Min Range: -7.4764
Max Act: 7.1014. Min Act: -0.1700
Data Index: 1657598 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4764. Min Range: -7.4764
Max Act: 7.0702. Min Act: -0.1700
Data Index: 2862157 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4764. Min Range: -7.4764
Max Act: 7.0389. Min Act: -0.1700
Data Index: 8438306 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4764. Min Range: -7.4764
Max Act: 7.0389. Min Act: -0.1700
Data Index: 1672441 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4764. Min Range: -7.4764
Max Act: 7.0389. Min Act: -0.1700
Data Index: 4735282 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4764. Min Range: -7.4764
Max Act: 7.0389. Min Act: -0.1700
Data Index: 4335169 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4764. Min Range: -7.4764
Max Act: 7.0077. Min Act: -0.1700
Data Index: 392752 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4764. Min Range: -7.4764
Max Act: 6.9764. Min Act: -0.1700
Data Index: 6218492 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4764. Min Range: -7.4764
Max Act: 6.9764. Min Act: -0.1700
Data Index: 7024296 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4764. Min Range: -7.4764
Max Act: 6.9764. Min Act: -0.1700
Data Index: 8261496 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4764. Min Range: -7.4764
Max Act: 6.9764. Min Act: -0.1700
Data Index: 1482841 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4764. Min Range: -7.4764
Max Act: 6.9764. Min Act: -0.1700
Data Index: 5352797 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4764. Min Range: -7.4764
Max Act: 6.9452. Min Act: -0.1700
Data Index: 5066344 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4764. Min Range: -7.4764
Max Act: 6.9452. Min Act: -0.1700
Data Index: 3801766 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #19