Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1308 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8065. Min Range: -6.8065
Max Act: 6.8065. Min Act: -0.1700
Data Index: 7278890 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8065. Min Range: -6.8065
Max Act: 6.2752. Min Act: -0.1700
Data Index: 876871 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8065. Min Range: -6.8065
Max Act: 6.0252. Min Act: -0.1700
Data Index: 6561901 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8065. Min Range: -6.8065
Max Act: 6.0252. Min Act: -0.1699
Data Index: 4498051 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8065. Min Range: -6.8065
Max Act: 6.0252. Min Act: -0.1700
Data Index: 7444882 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8065. Min Range: -6.8065
Max Act: 5.9940. Min Act: -0.1700
Data Index: 7074858 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8065. Min Range: -6.8065
Max Act: 6.0252. Min Act: -0.1700
Data Index: 4862093 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8065. Min Range: -6.8065
Max Act: 5.9315. Min Act: -0.1700
Data Index: 4272758 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8065. Min Range: -6.8065
Max Act: 5.9002. Min Act: -0.1700
Data Index: 4920924 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8065. Min Range: -6.8065
Max Act: 5.9002. Min Act: -0.1700
Data Index: 6806156 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8065. Min Range: -6.8065
Max Act: 5.9002. Min Act: -0.1700
Data Index: 8401003 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8065. Min Range: -6.8065
Max Act: 5.9002. Min Act: -0.1700
Data Index: 7131600 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8065. Min Range: -6.8065
Max Act: 5.9002. Min Act: -0.1700
Data Index: 635041 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8065. Min Range: -6.8065
Max Act: 5.8690. Min Act: -0.1699
Data Index: 1573467 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8065. Min Range: -6.8065
Max Act: 5.8690. Min Act: -0.1700
Data Index: 1877272 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8065. Min Range: -6.8065
Max Act: 5.8690. Min Act: -0.1700
Data Index: 2018455 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8065. Min Range: -6.8065
Max Act: 5.8690. Min Act: -0.1700
Data Index: 5523208 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8065. Min Range: -6.8065
Max Act: 5.8377. Min Act: -0.1700
Data Index: 4519067 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8065. Min Range: -6.8065
Max Act: 5.8377. Min Act: -0.1700
Data Index: 2659637 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8065. Min Range: -6.8065
Max Act: 5.8377. Min Act: -0.1700
Data Index: 5222372 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #19