Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5801 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7075. Min Range: -4.7075
Max Act: 4.7075. Min Act: -0.1700
Data Index: 6644063 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7075. Min Range: -4.7075
Max Act: 4.6762. Min Act: -0.1700
Data Index: 1385208 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7075. Min Range: -4.7075
Max Act: 4.6762. Min Act: -0.1700
Data Index: 1911145 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7075. Min Range: -4.7075
Max Act: 4.6762. Min Act: -0.1700
Data Index: 1720740 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7075. Min Range: -4.7075
Max Act: 4.6450. Min Act: -0.1700
Data Index: 3408294 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7075. Min Range: -4.7075
Max Act: 4.6450. Min Act: -0.1700
Data Index: 3408295 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7075. Min Range: -4.7075
Max Act: 4.6450. Min Act: -0.1700
Data Index: 7680849 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7075. Min Range: -4.7075
Max Act: 4.6137. Min Act: -0.1700
Data Index: 1652278 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7075. Min Range: -4.7075
Max Act: 4.5825. Min Act: -0.1700
Data Index: 4317900 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7075. Min Range: -4.7075
Max Act: 4.5825. Min Act: -0.1700
Data Index: 8655092 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7075. Min Range: -4.7075
Max Act: 4.5825. Min Act: -0.1700
Data Index: 8275330 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7075. Min Range: -4.7075
Max Act: 4.5825. Min Act: -0.1700
Data Index: 2976047 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7075. Min Range: -4.7075
Max Act: 4.5825. Min Act: -0.1700
Data Index: 4317904 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7075. Min Range: -4.7075
Max Act: 4.5512. Min Act: -0.1700
Data Index: 981885 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7075. Min Range: -4.7075
Max Act: 4.5512. Min Act: -0.1700
Data Index: 7198697 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7075. Min Range: -4.7075
Max Act: 4.5512. Min Act: -0.1700
Data Index: 6801569 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7075. Min Range: -4.7075
Max Act: 4.5200. Min Act: -0.1700
Data Index: 6380298 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7075. Min Range: -4.7075
Max Act: 4.5200. Min Act: -0.1700
Data Index: 2485158 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7075. Min Range: -4.7075
Max Act: 4.5200. Min Act: -0.1700
Data Index: 752904 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7075. Min Range: -4.7075
Max Act: 4.5200. Min Act: -0.1700
Data Index: 6801570 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #19