Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 23 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7455. Min Range: -5.7455
Max Act: 5.7455. Min Act: -0.1700
Data Index: 2375990 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7455. Min Range: -5.7455
Max Act: 4.6518. Min Act: -0.1700
Data Index: 5548142 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7455. Min Range: -5.7455
Max Act: 4.5892. Min Act: -0.1700
Data Index: 7077312 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7455. Min Range: -5.7455
Max Act: 4.5580. Min Act: -0.1700
Data Index: 1698725 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7455. Min Range: -5.7455
Max Act: 4.4642. Min Act: -0.1700
Data Index: 4650680 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7455. Min Range: -5.7455
Max Act: 4.4955. Min Act: -0.1700
Data Index: 3797016 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7455. Min Range: -5.7455
Max Act: 4.4642. Min Act: -0.1700
Data Index: 2176021 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7455. Min Range: -5.7455
Max Act: 4.4642. Min Act: -0.1700
Data Index: 5621797 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7455. Min Range: -5.7455
Max Act: 4.4955. Min Act: -0.1700
Data Index: 5764985 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7455. Min Range: -5.7455
Max Act: 4.4642. Min Act: -0.1700
Data Index: 1595631 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7455. Min Range: -5.7455
Max Act: 4.4642. Min Act: -0.1700
Data Index: 4805838 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7455. Min Range: -5.7455
Max Act: 4.4330. Min Act: -0.1700
Data Index: 5180102 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7455. Min Range: -5.7455
Max Act: 4.4017. Min Act: -0.1700
Data Index: 8726331 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7455. Min Range: -5.7455
Max Act: 4.4017. Min Act: -0.1700
Data Index: 6307830 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7455. Min Range: -5.7455
Max Act: 4.3705. Min Act: -0.1700
Data Index: 6123347 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7455. Min Range: -5.7455
Max Act: 4.3080. Min Act: -0.1700
Data Index: 1174153 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7455. Min Range: -5.7455
Max Act: 4.3080. Min Act: -0.1700
Data Index: 3280206 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7455. Min Range: -5.7455
Max Act: 4.3080. Min Act: -0.1700
Data Index: 6343577 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7455. Min Range: -5.7455
Max Act: 4.3080. Min Act: -0.1700
Data Index: 7322176 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7455. Min Range: -5.7455
Max Act: 4.2767. Min Act: -0.1700
Data Index: 271637 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #19