Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 891 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7017. Min Range: -6.7017
Max Act: 6.7017. Min Act: -0.1700
Data Index: 83766 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7017. Min Range: -6.7017
Max Act: 6.6705. Min Act: -0.1700
Data Index: 2497290 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7017. Min Range: -6.7017
Max Act: 6.6080. Min Act: -0.1700
Data Index: 8206391 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7017. Min Range: -6.7017
Max Act: 6.5455. Min Act: -0.1700
Data Index: 7888529 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7017. Min Range: -6.7017
Max Act: 6.4205. Min Act: -0.1700
Data Index: 5665281 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7017. Min Range: -6.7017
Max Act: 6.3892. Min Act: -0.1700
Data Index: 6079776 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7017. Min Range: -6.7017
Max Act: 6.4205. Min Act: -0.1700
Data Index: 7877781 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7017. Min Range: -6.7017
Max Act: 6.3267. Min Act: -0.1700
Data Index: 1008281 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7017. Min Range: -6.7017
Max Act: 6.2642. Min Act: -0.1700
Data Index: 8614817 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7017. Min Range: -6.7017
Max Act: 6.2642. Min Act: -0.1700
Data Index: 1060426 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7017. Min Range: -6.7017
Max Act: 6.2330. Min Act: -0.1700
Data Index: 2991314 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7017. Min Range: -6.7017
Max Act: 6.2017. Min Act: -0.1700
Data Index: 7322582 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7017. Min Range: -6.7017
Max Act: 6.2017. Min Act: -0.1700
Data Index: 4442435 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7017. Min Range: -6.7017
Max Act: 6.2017. Min Act: -0.1700
Data Index: 2216041 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7017. Min Range: -6.7017
Max Act: 6.1705. Min Act: -0.1700
Data Index: 2609263 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7017. Min Range: -6.7017
Max Act: 6.1705. Min Act: -0.1700
Data Index: 435527 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7017. Min Range: -6.7017
Max Act: 6.1392. Min Act: -0.1700
Data Index: 8713310 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7017. Min Range: -6.7017
Max Act: 6.1392. Min Act: -0.1700
Data Index: 785031 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7017. Min Range: -6.7017
Max Act: 6.1392. Min Act: -0.1700
Data Index: 4945259 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7017. Min Range: -6.7017
Max Act: 6.1080. Min Act: -0.1700
Data Index: 594731 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #19