Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 87 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2653. Min Range: -4.2653
Max Act: 4.2653. Min Act: -0.1700
Data Index: 3608572 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2653. Min Range: -4.2653
Max Act: 4.2653. Min Act: -0.1700
Data Index: 4653257 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2653. Min Range: -4.2653
Max Act: 4.2341. Min Act: -0.1700
Data Index: 4992692 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2653. Min Range: -4.2653
Max Act: 4.2341. Min Act: -0.1700
Data Index: 2244872 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2653. Min Range: -4.2653
Max Act: 4.2028. Min Act: -0.1700
Data Index: 1623479 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2653. Min Range: -4.2653
Max Act: 4.0778. Min Act: -0.1700
Data Index: 1406153 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2653. Min Range: -4.2653
Max Act: 4.1090. Min Act: -0.1700
Data Index: 861302 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2653. Min Range: -4.2653
Max Act: 4.1090. Min Act: -0.1700
Data Index: 8245133 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2653. Min Range: -4.2653
Max Act: 4.1090. Min Act: -0.1700
Data Index: 4992690 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2653. Min Range: -4.2653
Max Act: 4.1090. Min Act: -0.1700
Data Index: 2328263 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2653. Min Range: -4.2653
Max Act: 4.1090. Min Act: -0.1700
Data Index: 6819027 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2653. Min Range: -4.2653
Max Act: 4.0778. Min Act: -0.1700
Data Index: 3881081 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2653. Min Range: -4.2653
Max Act: 4.0778. Min Act: -0.1700
Data Index: 560383 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2653. Min Range: -4.2653
Max Act: 4.0778. Min Act: -0.1700
Data Index: 6824502 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2653. Min Range: -4.2653
Max Act: 4.0778. Min Act: -0.1700
Data Index: 6321761 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2653. Min Range: -4.2653
Max Act: 4.0778. Min Act: -0.1700
Data Index: 2247157 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2653. Min Range: -4.2653
Max Act: 4.0778. Min Act: -0.1700
Data Index: 3881082 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2653. Min Range: -4.2653
Max Act: 4.0465. Min Act: -0.1700
Data Index: 3552377 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2653. Min Range: -4.2653
Max Act: 4.0778. Min Act: -0.1700
Data Index: 913990 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2653. Min Range: -4.2653
Max Act: 4.0465. Min Act: -0.1700
Data Index: 4557247 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #19