Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1718 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0908. Min Range: -4.0908
Max Act: 4.0908. Min Act: -0.1700
Data Index: 376820 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0908. Min Range: -4.0908
Max Act: 3.8719. Min Act: -0.1700
Data Index: 214875 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0908. Min Range: -4.0908
Max Act: 3.7781. Min Act: -0.1700
Data Index: 6484783 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0908. Min Range: -4.0908
Max Act: 3.7625. Min Act: -0.1700
Data Index: 4171981 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0908. Min Range: -4.0908
Max Act: 3.7468. Min Act: -0.1700
Data Index: 5408005 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0908. Min Range: -4.0908
Max Act: 3.7468. Min Act: -0.1700
Data Index: 3559971 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0908. Min Range: -4.0908
Max Act: 3.7468. Min Act: -0.1700
Data Index: 6773676 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0908. Min Range: -4.0908
Max Act: 3.7468. Min Act: -0.1700
Data Index: 5662598 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0908. Min Range: -4.0908
Max Act: 3.7312. Min Act: -0.1700
Data Index: 5974130 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0908. Min Range: -4.0908
Max Act: 3.7312. Min Act: -0.1700
Data Index: 5774517 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0908. Min Range: -4.0908
Max Act: 3.6999. Min Act: -0.1700
Data Index: 4564287 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0908. Min Range: -4.0908
Max Act: 3.6999. Min Act: -0.1700
Data Index: 129247 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0908. Min Range: -4.0908
Max Act: 3.6530. Min Act: -0.1700
Data Index: 5776196 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0908. Min Range: -4.0908
Max Act: 3.6373. Min Act: -0.1700
Data Index: 538766 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0908. Min Range: -4.0908
Max Act: 3.6530. Min Act: -0.1700
Data Index: 7666839 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0908. Min Range: -4.0908
Max Act: 3.6686. Min Act: -0.1700
Data Index: 2724206 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0908. Min Range: -4.0908
Max Act: 3.6530. Min Act: -0.1700
Data Index: 7835496 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0908. Min Range: -4.0908
Max Act: 3.6217. Min Act: -0.1700
Data Index: 7694016 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0908. Min Range: -4.0908
Max Act: 3.6217. Min Act: -0.1700
Data Index: 2634474 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0908. Min Range: -4.0908
Max Act: 3.6217. Min Act: -0.1700
Data Index: 7931789 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #19