Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4407 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0879. Min Range: -8.0879
Max Act: 8.0879. Min Act: -0.1700
Data Index: 464578 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0879. Min Range: -8.0879
Max Act: 7.9629. Min Act: -0.1700
Data Index: 6608090 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0879. Min Range: -8.0879
Max Act: 7.9629. Min Act: -0.1700
Data Index: 2548905 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0879. Min Range: -8.0879
Max Act: 7.9629. Min Act: -0.1700
Data Index: 4388448 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0879. Min Range: -8.0879
Max Act: 7.9629. Min Act: -0.1700
Data Index: 962404 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0879. Min Range: -8.0879
Max Act: 7.9629. Min Act: -0.1700
Data Index: 6963409 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0879. Min Range: -8.0879
Max Act: 7.9004. Min Act: -0.1700
Data Index: 2189839 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0879. Min Range: -8.0879
Max Act: 7.9004. Min Act: -0.1700
Data Index: 4723119 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0879. Min Range: -8.0879
Max Act: 7.8379. Min Act: -0.1700
Data Index: 6632540 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0879. Min Range: -8.0879
Max Act: 7.8379. Min Act: -0.1700
Data Index: 7301509 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0879. Min Range: -8.0879
Max Act: 7.8379. Min Act: -0.1700
Data Index: 8686719 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0879. Min Range: -8.0879
Max Act: 7.8379. Min Act: -0.1700
Data Index: 1025743 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0879. Min Range: -8.0879
Max Act: 7.7754. Min Act: -0.1700
Data Index: 5678771 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0879. Min Range: -8.0879
Max Act: 7.7754. Min Act: -0.1700
Data Index: 5718117 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0879. Min Range: -8.0879
Max Act: 7.7129. Min Act: -0.1700
Data Index: 5842666 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0879. Min Range: -8.0879
Max Act: 7.7129. Min Act: -0.1700
Data Index: 4661737 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0879. Min Range: -8.0879
Max Act: 7.7129. Min Act: -0.1700
Data Index: 2085611 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0879. Min Range: -8.0879
Max Act: 7.7129. Min Act: -0.1700
Data Index: 4243478 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0879. Min Range: -8.0879
Max Act: 7.7129. Min Act: -0.1700
Data Index: 2966165 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0879. Min Range: -8.0879
Max Act: 7.7129. Min Act: -0.1700
Data Index: 557341 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #19