Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1558 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0654. Min Range: -5.0654
Max Act: 5.0654. Min Act: -0.1700
Data Index: 6707885 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0654. Min Range: -5.0654
Max Act: 5.0654. Min Act: -0.1700
Data Index: 1431101 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0654. Min Range: -5.0654
Max Act: 4.9404. Min Act: -0.1700
Data Index: 7871431 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0654. Min Range: -5.0654
Max Act: 4.9404. Min Act: -0.1700
Data Index: 1533648 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0654. Min Range: -5.0654
Max Act: 4.9404. Min Act: -0.1700
Data Index: 7495702 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0654. Min Range: -5.0654
Max Act: 4.9091. Min Act: -0.1700
Data Index: 4958647 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0654. Min Range: -5.0654
Max Act: 4.8779. Min Act: -0.1700
Data Index: 2492041 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0654. Min Range: -5.0654
Max Act: 4.8779. Min Act: -0.1700
Data Index: 2593246 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0654. Min Range: -5.0654
Max Act: 4.8779. Min Act: -0.1700
Data Index: 4171826 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0654. Min Range: -5.0654
Max Act: 4.8779. Min Act: -0.1700
Data Index: 3101578 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0654. Min Range: -5.0654
Max Act: 4.8779. Min Act: -0.1700
Data Index: 21888 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0654. Min Range: -5.0654
Max Act: 4.8466. Min Act: -0.1700
Data Index: 1040260 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0654. Min Range: -5.0654
Max Act: 4.7841. Min Act: -0.1700
Data Index: 1618438 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0654. Min Range: -5.0654
Max Act: 4.7841. Min Act: -0.1700
Data Index: 5309756 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0654. Min Range: -5.0654
Max Act: 4.7841. Min Act: -0.1700
Data Index: 311187 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0654. Min Range: -5.0654
Max Act: 4.7529. Min Act: -0.1700
Data Index: 3527474 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0654. Min Range: -5.0654
Max Act: 4.7841. Min Act: -0.1700
Data Index: 4909265 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0654. Min Range: -5.0654
Max Act: 4.7841. Min Act: -0.1700
Data Index: 1750887 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0654. Min Range: -5.0654
Max Act: 4.7841. Min Act: -0.1700
Data Index: 6087386 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0654. Min Range: -5.0654
Max Act: 4.7529. Min Act: -0.1700
Data Index: 1310599 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19