Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4710 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0139. Min Range: -6.0139
Max Act: 6.0139. Min Act: -0.1700
Data Index: 8188144 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0139. Min Range: -6.0139
Max Act: 5.9514. Min Act: -0.1700
Data Index: 7787164 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0139. Min Range: -6.0139
Max Act: 5.8889. Min Act: -0.1700
Data Index: 4972388 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0139. Min Range: -6.0139
Max Act: 5.7952. Min Act: -0.1700
Data Index: 8436277 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0139. Min Range: -6.0139
Max Act: 5.7952. Min Act: -0.1700
Data Index: 4615585 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0139. Min Range: -6.0139
Max Act: 5.7639. Min Act: -0.1700
Data Index: 6748828 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0139. Min Range: -6.0139
Max Act: 5.7639. Min Act: -0.1700
Data Index: 4023150 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0139. Min Range: -6.0139
Max Act: 5.7639. Min Act: -0.1700
Data Index: 1477263 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0139. Min Range: -6.0139
Max Act: 5.7014. Min Act: -0.1700
Data Index: 7241171 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0139. Min Range: -6.0139
Max Act: 5.6702. Min Act: -0.1700
Data Index: 2102038 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0139. Min Range: -6.0139
Max Act: 5.7014. Min Act: -0.1700
Data Index: 6564619 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0139. Min Range: -6.0139
Max Act: 5.6702. Min Act: -0.1700
Data Index: 5676394 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0139. Min Range: -6.0139
Max Act: 5.6389. Min Act: -0.1700
Data Index: 3767716 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0139. Min Range: -6.0139
Max Act: 5.6077. Min Act: -0.1700
Data Index: 2935324 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0139. Min Range: -6.0139
Max Act: 5.6389. Min Act: -0.1700
Data Index: 2207702 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0139. Min Range: -6.0139
Max Act: 5.6389. Min Act: -0.1700
Data Index: 2691216 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0139. Min Range: -6.0139
Max Act: 5.6702. Min Act: -0.1700
Data Index: 1469640 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0139. Min Range: -6.0139
Max Act: 5.6389. Min Act: -0.1700
Data Index: 3432404 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0139. Min Range: -6.0139
Max Act: 5.6389. Min Act: -0.1700
Data Index: 2950415 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0139. Min Range: -6.0139
Max Act: 5.6389. Min Act: -0.1700
Data Index: 5306122 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #19