Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1959 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0913. Min Range: -5.0913
Max Act: 5.0913. Min Act: -0.1700
Data Index: 7599386 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0913. Min Range: -5.0913
Max Act: 4.9350. Min Act: -0.1700
Data Index: 711226 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0913. Min Range: -5.0913
Max Act: 4.9350. Min Act: -0.1700
Data Index: 481657 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0913. Min Range: -5.0913
Max Act: 4.9038. Min Act: -0.1700
Data Index: 1870111 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0913. Min Range: -5.0913
Max Act: 4.8725. Min Act: -0.1700
Data Index: 4085837 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0913. Min Range: -5.0913
Max Act: 4.8725. Min Act: -0.1700
Data Index: 1147872 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0913. Min Range: -5.0913
Max Act: 4.7788. Min Act: -0.1700
Data Index: 1927613 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0913. Min Range: -5.0913
Max Act: 4.8100. Min Act: -0.1700
Data Index: 8621736 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0913. Min Range: -5.0913
Max Act: 4.8100. Min Act: -0.1700
Data Index: 5430321 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0913. Min Range: -5.0913
Max Act: 4.7788. Min Act: -0.1700
Data Index: 5502196 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0913. Min Range: -5.0913
Max Act: 4.8100. Min Act: -0.1700
Data Index: 7679325 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0913. Min Range: -5.0913
Max Act: 4.8100. Min Act: -0.1700
Data Index: 7732023 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0913. Min Range: -5.0913
Max Act: 4.7788. Min Act: -0.1700
Data Index: 921345 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0913. Min Range: -5.0913
Max Act: 4.8100. Min Act: -0.1700
Data Index: 6907761 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0913. Min Range: -5.0913
Max Act: 4.7788. Min Act: -0.1700
Data Index: 4500929 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0913. Min Range: -5.0913
Max Act: 4.7788. Min Act: -0.1700
Data Index: 746112 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0913. Min Range: -5.0913
Max Act: 4.7788. Min Act: -0.1700
Data Index: 5727467 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0913. Min Range: -5.0913
Max Act: 4.7788. Min Act: -0.1700
Data Index: 8507662 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0913. Min Range: -5.0913
Max Act: 4.7475. Min Act: -0.1700
Data Index: 1914888 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0913. Min Range: -5.0913
Max Act: 4.7788. Min Act: -0.1700
Data Index: 5186966 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #19