Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 213 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 19.9098. Min Range: -19.9098
Max Act: 19.9098. Min Act: -0.1700
Data Index: 2109317 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 19.9098. Min Range: -19.9098
Max Act: 19.6598. Min Act: -0.1700
Data Index: 1900459 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 19.9098. Min Range: -19.9098
Max Act: 19.5348. Min Act: -0.1700
Data Index: 597961 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 19.9098. Min Range: -19.9098
Max Act: 19.5348. Min Act: -0.1700
Data Index: 597962 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 19.9098. Min Range: -19.9098
Max Act: 19.5348. Min Act: -0.1700
Data Index: 4086345 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 19.9098. Min Range: -19.9098
Max Act: 19.5348. Min Act: -0.1700
Data Index: 446483 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 19.9098. Min Range: -19.9098
Max Act: 19.4098. Min Act: -0.1700
Data Index: 2588586 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 19.9098. Min Range: -19.9098
Max Act: 19.4098. Min Act: -0.1700
Data Index: 2099981 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 19.9098. Min Range: -19.9098
Max Act: 19.2848. Min Act: -0.1700
Data Index: 4591739 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 19.9098. Min Range: -19.9098
Max Act: 19.2848. Min Act: -0.1700
Data Index: 7622381 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 19.9098. Min Range: -19.9098
Max Act: 19.1598. Min Act: -0.1700
Data Index: 2667773 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 19.9098. Min Range: -19.9098
Max Act: 19.1598. Min Act: -0.1700
Data Index: 8182030 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 19.9098. Min Range: -19.9098
Max Act: 19.0348. Min Act: -0.1700
Data Index: 3152171 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 19.9098. Min Range: -19.9098
Max Act: 19.0348. Min Act: -0.1700
Data Index: 5285629 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 19.9098. Min Range: -19.9098
Max Act: 19.0348. Min Act: -0.1685
Data Index: 446480 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 19.9098. Min Range: -19.9098
Max Act: 19.0348. Min Act: -0.1700
Data Index: 2697295 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 19.9098. Min Range: -19.9098
Max Act: 19.0348. Min Act: -0.1700
Data Index: 7622373 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 19.9098. Min Range: -19.9098
Max Act: 18.9098. Min Act: -0.1700
Data Index: 4524148 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 19.9098. Min Range: -19.9098
Max Act: 18.9098. Min Act: -0.1700
Data Index: 7799673 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 19.9098. Min Range: -19.9098
Max Act: 18.9098. Min Act: -0.1700
Data Index: 6710354 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #19