Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4805 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1401. Min Range: -6.1401
Max Act: 6.1401. Min Act: -0.1700
Data Index: 3163851 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1401. Min Range: -6.1401
Max Act: 6.0463. Min Act: -0.1700
Data Index: 1820257 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1401. Min Range: -6.1401
Max Act: 6.0151. Min Act: -0.1700
Data Index: 8418716 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1401. Min Range: -6.1401
Max Act: 6.0151. Min Act: -0.1700
Data Index: 421805 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1401. Min Range: -6.1401
Max Act: 5.9838. Min Act: -0.1700
Data Index: 289231 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1401. Min Range: -6.1401
Max Act: 5.9838. Min Act: -0.1700
Data Index: 5619536 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1401. Min Range: -6.1401
Max Act: 5.9526. Min Act: -0.1700
Data Index: 4950768 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1401. Min Range: -6.1401
Max Act: 5.9526. Min Act: -0.1700
Data Index: 8281225 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1401. Min Range: -6.1401
Max Act: 5.9526. Min Act: -0.1700
Data Index: 3163842 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1401. Min Range: -6.1401
Max Act: 5.9526. Min Act: -0.1700
Data Index: 2924545 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1401. Min Range: -6.1401
Max Act: 5.9213. Min Act: -0.1700
Data Index: 8281227 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1401. Min Range: -6.1401
Max Act: 5.9213. Min Act: -0.1700
Data Index: 3163841 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1401. Min Range: -6.1401
Max Act: 5.8901. Min Act: -0.1700
Data Index: 5072846 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1401. Min Range: -6.1401
Max Act: 5.9213. Min Act: -0.1700
Data Index: 1567325 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1401. Min Range: -6.1401
Max Act: 5.8901. Min Act: -0.1700
Data Index: 8456764 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1401. Min Range: -6.1401
Max Act: 5.8588. Min Act: -0.1700
Data Index: 7907396 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1401. Min Range: -6.1401
Max Act: 5.8588. Min Act: -0.1700
Data Index: 4480504 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1401. Min Range: -6.1401
Max Act: 5.8588. Min Act: -0.1700
Data Index: 3163838 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1401. Min Range: -6.1401
Max Act: 5.8276. Min Act: -0.1700
Data Index: 5754531 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1401. Min Range: -6.1401
Max Act: 5.7963. Min Act: -0.1700
Data Index: 2011362 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #19