Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6233 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4712. Min Range: -6.4712
Max Act: 6.4712. Min Act: -0.1700
Data Index: 1156292 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4712. Min Range: -6.4712
Max Act: 6.4712. Min Act: -0.1700
Data Index: 2650276 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4712. Min Range: -6.4712
Max Act: 6.4712. Min Act: -0.1700
Data Index: 6848776 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4712. Min Range: -6.4712
Max Act: 6.4399. Min Act: -0.1700
Data Index: 2189067 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4712. Min Range: -6.4712
Max Act: 6.4087. Min Act: -0.1700
Data Index: 7457087 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4712. Min Range: -6.4712
Max Act: 6.3774. Min Act: -0.1700
Data Index: 2189071 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4712. Min Range: -6.4712
Max Act: 6.3774. Min Act: -0.1700
Data Index: 8530503 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4712. Min Range: -6.4712
Max Act: 6.3774. Min Act: -0.1700
Data Index: 2696161 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4712. Min Range: -6.4712
Max Act: 6.3774. Min Act: -0.1700
Data Index: 8042904 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4712. Min Range: -6.4712
Max Act: 6.3149. Min Act: -0.1700
Data Index: 573975 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4712. Min Range: -6.4712
Max Act: 6.3149. Min Act: -0.1700
Data Index: 5856429 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4712. Min Range: -6.4712
Max Act: 6.3462. Min Act: -0.1700
Data Index: 2847739 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4712. Min Range: -6.4712
Max Act: 6.3149. Min Act: -0.1700
Data Index: 4833871 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4712. Min Range: -6.4712
Max Act: 6.2837. Min Act: -0.1700
Data Index: 4246418 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4712. Min Range: -6.4712
Max Act: 6.2837. Min Act: -0.1700
Data Index: 3601984 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4712. Min Range: -6.4712
Max Act: 6.2524. Min Act: -0.1700
Data Index: 2906717 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4712. Min Range: -6.4712
Max Act: 6.2212. Min Act: -0.1700
Data Index: 2448209 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4712. Min Range: -6.4712
Max Act: 6.2212. Min Act: -0.1700
Data Index: 3237252 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4712. Min Range: -6.4712
Max Act: 6.2212. Min Act: -0.1700
Data Index: 7080842 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4712. Min Range: -6.4712
Max Act: 6.1899. Min Act: -0.1700
Data Index: 7360662 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #19