Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3630 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6659. Min Range: -3.6659
Max Act: 3.6659. Min Act: -0.1700
Data Index: 5833660 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6659. Min Range: -3.6659
Max Act: 3.6659. Min Act: -0.1700
Data Index: 2932331 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6659. Min Range: -3.6659
Max Act: 3.6659. Min Act: -0.1700
Data Index: 2469821 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6659. Min Range: -3.6659
Max Act: 3.6659. Min Act: -0.1700
Data Index: 4300078 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6659. Min Range: -3.6659
Max Act: 3.6659. Min Act: -0.1700
Data Index: 2564136 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6659. Min Range: -3.6659
Max Act: 3.6346. Min Act: -0.1700
Data Index: 8739749 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6659. Min Range: -3.6659
Max Act: 3.6346. Min Act: -0.1700
Data Index: 6702712 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6659. Min Range: -3.6659
Max Act: 3.6346. Min Act: -0.1700
Data Index: 8450038 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6659. Min Range: -3.6659
Max Act: 3.6346. Min Act: -0.1700
Data Index: 7913604 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6659. Min Range: -3.6659
Max Act: 3.6346. Min Act: -0.1700
Data Index: 905869 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6659. Min Range: -3.6659
Max Act: 3.6346. Min Act: -0.1700
Data Index: 7391300 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6659. Min Range: -3.6659
Max Act: 3.6346. Min Act: -0.1700
Data Index: 5228461 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6659. Min Range: -3.6659
Max Act: 3.6033. Min Act: -0.1700
Data Index: 544989 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6659. Min Range: -3.6659
Max Act: 3.6033. Min Act: -0.1700
Data Index: 5514022 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6659. Min Range: -3.6659
Max Act: 3.6033. Min Act: -0.1700
Data Index: 5097612 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6659. Min Range: -3.6659
Max Act: 3.6033. Min Act: -0.1700
Data Index: 7286370 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6659. Min Range: -3.6659
Max Act: 3.6033. Min Act: -0.1700
Data Index: 2418989 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6659. Min Range: -3.6659
Max Act: 3.6033. Min Act: -0.1700
Data Index: 1972170 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6659. Min Range: -3.6659
Max Act: 3.6033. Min Act: -0.1700
Data Index: 1819897 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6659. Min Range: -3.6659
Max Act: 3.6033. Min Act: -0.1700
Data Index: 1767844 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19