Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5858 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1072. Min Range: -5.1072
Max Act: 5.1072. Min Act: -0.1700
Data Index: 7676030 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1072. Min Range: -5.1072
Max Act: 5.0759. Min Act: -0.1700
Data Index: 5056684 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1072. Min Range: -5.1072
Max Act: 5.0447. Min Act: -0.1700
Data Index: 3112266 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1072. Min Range: -5.1072
Max Act: 5.0447. Min Act: -0.1700
Data Index: 4931637 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1072. Min Range: -5.1072
Max Act: 5.0134. Min Act: -0.1700
Data Index: 5982232 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1072. Min Range: -5.1072
Max Act: 5.0134. Min Act: -0.1700
Data Index: 578073 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1072. Min Range: -5.1072
Max Act: 4.9822. Min Act: -0.1700
Data Index: 3487529 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1072. Min Range: -5.1072
Max Act: 4.9822. Min Act: -0.1700
Data Index: 6009735 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1072. Min Range: -5.1072
Max Act: 4.9822. Min Act: -0.1700
Data Index: 1701835 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1072. Min Range: -5.1072
Max Act: 4.9822. Min Act: -0.1700
Data Index: 5916846 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1072. Min Range: -5.1072
Max Act: 4.9509. Min Act: -0.1700
Data Index: 7492262 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1072. Min Range: -5.1072
Max Act: 4.9509. Min Act: -0.1700
Data Index: 46491 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1072. Min Range: -5.1072
Max Act: 4.9197. Min Act: -0.1700
Data Index: 6185539 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1072. Min Range: -5.1072
Max Act: 4.9197. Min Act: -0.1700
Data Index: 8736263 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1072. Min Range: -5.1072
Max Act: 4.9197. Min Act: -0.1700
Data Index: 6240186 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1072. Min Range: -5.1072
Max Act: 4.8884. Min Act: -0.1700
Data Index: 4801490 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1072. Min Range: -5.1072
Max Act: 4.8884. Min Act: -0.1700
Data Index: 3107923 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1072. Min Range: -5.1072
Max Act: 4.8884. Min Act: -0.1700
Data Index: 5089334 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1072. Min Range: -5.1072
Max Act: 4.8572. Min Act: -0.1700
Data Index: 3356669 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1072. Min Range: -5.1072
Max Act: 4.9197. Min Act: -0.1700
Data Index: 3766429 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #19