Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2199 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3109. Min Range: -8.3109
Max Act: 8.3109. Min Act: -0.1700
Data Index: 4716039 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3109. Min Range: -8.3109
Max Act: 8.2484. Min Act: -0.1700
Data Index: 4659621 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3109. Min Range: -8.3109
Max Act: 8.1859. Min Act: -0.1700
Data Index: 4789435 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3109. Min Range: -8.3109
Max Act: 8.0609. Min Act: -0.1700
Data Index: 7623449 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3109. Min Range: -8.3109
Max Act: 8.0609. Min Act: -0.1700
Data Index: 5006462 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3109. Min Range: -8.3109
Max Act: 7.9984. Min Act: -0.1700
Data Index: 6270427 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3109. Min Range: -8.3109
Max Act: 7.9359. Min Act: -0.1700
Data Index: 648572 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3109. Min Range: -8.3109
Max Act: 7.9359. Min Act: -0.1700
Data Index: 4840695 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3109. Min Range: -8.3109
Max Act: 7.9359. Min Act: -0.1700
Data Index: 2025852 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3109. Min Range: -8.3109
Max Act: 7.8734. Min Act: -0.1700
Data Index: 4990234 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3109. Min Range: -8.3109
Max Act: 7.8734. Min Act: -0.1700
Data Index: 3952224 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3109. Min Range: -8.3109
Max Act: 7.8734. Min Act: -0.1700
Data Index: 846566 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3109. Min Range: -8.3109
Max Act: 7.8109. Min Act: -0.1700
Data Index: 8556365 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3109. Min Range: -8.3109
Max Act: 7.8109. Min Act: -0.1700
Data Index: 7588756 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3109. Min Range: -8.3109
Max Act: 7.8109. Min Act: -0.1700
Data Index: 451931 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3109. Min Range: -8.3109
Max Act: 7.7484. Min Act: -0.1700
Data Index: 4626485 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3109. Min Range: -8.3109
Max Act: 7.8109. Min Act: -0.1700
Data Index: 5848915 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3109. Min Range: -8.3109
Max Act: 7.8109. Min Act: -0.1700
Data Index: 1564584 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3109. Min Range: -8.3109
Max Act: 7.7484. Min Act: -0.1700
Data Index: 769642 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3109. Min Range: -8.3109
Max Act: 7.7484. Min Act: -0.1700
Data Index: 1298007 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #19