Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3526 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2050. Min Range: -7.2050
Max Act: 7.2050. Min Act: -0.1700
Data Index: 3906713 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2050. Min Range: -7.2050
Max Act: 7.2050. Min Act: -0.1700
Data Index: 4047553 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2050. Min Range: -7.2050
Max Act: 7.2050. Min Act: -0.1700
Data Index: 5443806 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2050. Min Range: -7.2050
Max Act: 7.0487. Min Act: -0.1700
Data Index: 6605086 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2050. Min Range: -7.2050
Max Act: 7.0800. Min Act: -0.1700
Data Index: 6731588 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2050. Min Range: -7.2050
Max Act: 7.0175. Min Act: -0.1700
Data Index: 647240 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2050. Min Range: -7.2050
Max Act: 7.0175. Min Act: -0.1700
Data Index: 6003976 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2050. Min Range: -7.2050
Max Act: 7.0175. Min Act: -0.1700
Data Index: 651654 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2050. Min Range: -7.2050
Max Act: 7.0175. Min Act: -0.1700
Data Index: 1957216 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2050. Min Range: -7.2050
Max Act: 6.9550. Min Act: -0.1700
Data Index: 5236882 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2050. Min Range: -7.2050
Max Act: 6.9550. Min Act: -0.1700
Data Index: 2737380 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2050. Min Range: -7.2050
Max Act: 6.9237. Min Act: -0.1700
Data Index: 5419971 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2050. Min Range: -7.2050
Max Act: 6.8612. Min Act: -0.1700
Data Index: 2026335 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2050. Min Range: -7.2050
Max Act: 6.8612. Min Act: -0.1700
Data Index: 5647923 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2050. Min Range: -7.2050
Max Act: 6.8300. Min Act: -0.1700
Data Index: 146689 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2050. Min Range: -7.2050
Max Act: 6.7987. Min Act: -0.1700
Data Index: 5809470 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2050. Min Range: -7.2050
Max Act: 6.7987. Min Act: -0.1700
Data Index: 4677437 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2050. Min Range: -7.2050
Max Act: 6.8300. Min Act: -0.1700
Data Index: 3729355 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2050. Min Range: -7.2050
Max Act: 6.7987. Min Act: -0.1700
Data Index: 5690091 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2050. Min Range: -7.2050
Max Act: 6.7987. Min Act: -0.1700
Data Index: 383218 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #19