Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3560 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6690. Min Range: -4.6690
Max Act: 4.6690. Min Act: -0.1700
Data Index: 466795 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6690. Min Range: -4.6690
Max Act: 4.5440. Min Act: -0.1700
Data Index: 2174146 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6690. Min Range: -4.6690
Max Act: 4.5440. Min Act: -0.1700
Data Index: 6090090 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6690. Min Range: -4.6690
Max Act: 4.5440. Min Act: -0.1700
Data Index: 3161144 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6690. Min Range: -4.6690
Max Act: 4.4815. Min Act: -0.1700
Data Index: 6400641 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6690. Min Range: -4.6690
Max Act: 4.4190. Min Act: -0.1700
Data Index: 3735624 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6690. Min Range: -4.6690
Max Act: 4.4503. Min Act: -0.1700
Data Index: 1556942 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6690. Min Range: -4.6690
Max Act: 4.4190. Min Act: -0.1700
Data Index: 7943439 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6690. Min Range: -4.6690
Max Act: 4.3878. Min Act: -0.1700
Data Index: 8782708 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6690. Min Range: -4.6690
Max Act: 4.3878. Min Act: -0.1700
Data Index: 3506105 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6690. Min Range: -4.6690
Max Act: 4.3878. Min Act: -0.1700
Data Index: 4641669 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6690. Min Range: -4.6690
Max Act: 4.3253. Min Act: -0.1700
Data Index: 5987951 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6690. Min Range: -4.6690
Max Act: 4.3878. Min Act: -0.1700
Data Index: 1385873 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6690. Min Range: -4.6690
Max Act: 4.3565. Min Act: -0.1700
Data Index: 1241953 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6690. Min Range: -4.6690
Max Act: 4.3565. Min Act: -0.1700
Data Index: 5893291 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6690. Min Range: -4.6690
Max Act: 4.3253. Min Act: -0.1700
Data Index: 4671102 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6690. Min Range: -4.6690
Max Act: 4.3565. Min Act: -0.1700
Data Index: 6780436 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6690. Min Range: -4.6690
Max Act: 4.3565. Min Act: -0.1700
Data Index: 3735625 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6690. Min Range: -4.6690
Max Act: 4.3878. Min Act: -0.1700
Data Index: 2335213 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6690. Min Range: -4.6690
Max Act: 4.3565. Min Act: -0.1700
Data Index: 4071378 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #19