Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1841 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0998. Min Range: -5.0998
Max Act: 5.0998. Min Act: -0.1700
Data Index: 5479166 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0998. Min Range: -5.0998
Max Act: 5.0373. Min Act: -0.1700
Data Index: 7988498 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0998. Min Range: -5.0998
Max Act: 4.9123. Min Act: -0.1700
Data Index: 1511909 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0998. Min Range: -5.0998
Max Act: 4.9123. Min Act: -0.1700
Data Index: 6165882 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0998. Min Range: -5.0998
Max Act: 4.8810. Min Act: -0.1700
Data Index: 5479168 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0998. Min Range: -5.0998
Max Act: 4.8810. Min Act: -0.1700
Data Index: 7680292 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0998. Min Range: -5.0998
Max Act: 4.8498. Min Act: -0.1700
Data Index: 3010693 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0998. Min Range: -5.0998
Max Act: 4.8185. Min Act: -0.1700
Data Index: 3560461 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0998. Min Range: -5.0998
Max Act: 4.8185. Min Act: -0.1700
Data Index: 34428 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0998. Min Range: -5.0998
Max Act: 4.8185. Min Act: -0.1700
Data Index: 3537310 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0998. Min Range: -5.0998
Max Act: 4.8185. Min Act: -0.1700
Data Index: 3482333 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0998. Min Range: -5.0998
Max Act: 4.8185. Min Act: -0.1700
Data Index: 6568425 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0998. Min Range: -5.0998
Max Act: 4.7560. Min Act: -0.1700
Data Index: 3034125 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0998. Min Range: -5.0998
Max Act: 4.7560. Min Act: -0.1700
Data Index: 5153890 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0998. Min Range: -5.0998
Max Act: 4.7873. Min Act: -0.1700
Data Index: 7696423 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0998. Min Range: -5.0998
Max Act: 4.7560. Min Act: -0.1700
Data Index: 590210 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0998. Min Range: -5.0998
Max Act: 4.7248. Min Act: -0.1700
Data Index: 1831530 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0998. Min Range: -5.0998
Max Act: 4.7560. Min Act: -0.1700
Data Index: 3010689 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0998. Min Range: -5.0998
Max Act: 4.7248. Min Act: -0.1700
Data Index: 4670182 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0998. Min Range: -5.0998
Max Act: 4.7248. Min Act: -0.1700
Data Index: 3906729 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #19