Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 968 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9361. Min Range: -5.9361
Max Act: 5.9361. Min Act: -0.1700
Data Index: 4133371 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9361. Min Range: -5.9361
Max Act: 5.9049. Min Act: -0.1700
Data Index: 7237287 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9361. Min Range: -5.9361
Max Act: 5.8736. Min Act: -0.1700
Data Index: 8430400 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9361. Min Range: -5.9361
Max Act: 5.9049. Min Act: -0.1700
Data Index: 5725082 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9361. Min Range: -5.9361
Max Act: 5.8424. Min Act: -0.1700
Data Index: 1894446 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9361. Min Range: -5.9361
Max Act: 5.8424. Min Act: -0.1700
Data Index: 6740153 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9361. Min Range: -5.9361
Max Act: 5.8424. Min Act: -0.1700
Data Index: 7733107 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9361. Min Range: -5.9361
Max Act: 5.8111. Min Act: -0.1700
Data Index: 8139780 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9361. Min Range: -5.9361
Max Act: 5.8111. Min Act: -0.1700
Data Index: 5478123 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9361. Min Range: -5.9361
Max Act: 5.8111. Min Act: -0.1700
Data Index: 1220545 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9361. Min Range: -5.9361
Max Act: 5.8111. Min Act: -0.1700
Data Index: 8494926 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9361. Min Range: -5.9361
Max Act: 5.7799. Min Act: -0.1700
Data Index: 8344158 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9361. Min Range: -5.9361
Max Act: 5.7799. Min Act: -0.1700
Data Index: 5656204 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9361. Min Range: -5.9361
Max Act: 5.7799. Min Act: -0.1700
Data Index: 8439744 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9361. Min Range: -5.9361
Max Act: 5.7486. Min Act: -0.1700
Data Index: 3852860 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9361. Min Range: -5.9361
Max Act: 5.7486. Min Act: -0.1700
Data Index: 4159949 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9361. Min Range: -5.9361
Max Act: 5.7486. Min Act: -0.1700
Data Index: 2298698 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9361. Min Range: -5.9361
Max Act: 5.7486. Min Act: -0.1700
Data Index: 8015124 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9361. Min Range: -5.9361
Max Act: 5.6861. Min Act: -0.1700
Data Index: 6042704 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9361. Min Range: -5.9361
Max Act: 5.7174. Min Act: -0.1700
Data Index: 1728188 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19