Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2384 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1073. Min Range: -8.1073
Max Act: 8.1073. Min Act: -0.1700
Data Index: 2966095 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1073. Min Range: -8.1073
Max Act: 8.0448. Min Act: -0.1700
Data Index: 5206231 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1073. Min Range: -8.1073
Max Act: 7.9510. Min Act: -0.1700
Data Index: 6766892 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1073. Min Range: -8.1073
Max Act: 7.9198. Min Act: -0.1700
Data Index: 2558092 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1073. Min Range: -8.1073
Max Act: 7.8573. Min Act: -0.1700
Data Index: 2677543 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1073. Min Range: -8.1073
Max Act: 7.8885. Min Act: -0.1700
Data Index: 6978135 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1073. Min Range: -8.1073
Max Act: 7.7948. Min Act: -0.1700
Data Index: 3254881 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1073. Min Range: -8.1073
Max Act: 7.7948. Min Act: -0.1700
Data Index: 398709 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1073. Min Range: -8.1073
Max Act: 7.7635. Min Act: -0.1700
Data Index: 5919471 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1073. Min Range: -8.1073
Max Act: 7.7635. Min Act: -0.1700
Data Index: 2148412 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1073. Min Range: -8.1073
Max Act: 7.7010. Min Act: -0.1700
Data Index: 150890 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1073. Min Range: -8.1073
Max Act: 7.7010. Min Act: -0.1700
Data Index: 5859279 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1073. Min Range: -8.1073
Max Act: 7.6385. Min Act: -0.1700
Data Index: 1480672 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1073. Min Range: -8.1073
Max Act: 7.6385. Min Act: -0.1700
Data Index: 2986373 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1073. Min Range: -8.1073
Max Act: 7.6385. Min Act: -0.1700
Data Index: 5693146 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1073. Min Range: -8.1073
Max Act: 7.6073. Min Act: -0.1700
Data Index: 278720 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1073. Min Range: -8.1073
Max Act: 7.6073. Min Act: -0.1700
Data Index: 596934 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1073. Min Range: -8.1073
Max Act: 7.5760. Min Act: -0.1700
Data Index: 4876230 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1073. Min Range: -8.1073
Max Act: 7.5760. Min Act: -0.1700
Data Index: 8793635 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1073. Min Range: -8.1073
Max Act: 7.5448. Min Act: -0.1700
Data Index: 2724343 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #19