Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2267 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5156. Min Range: -8.5156
Max Act: 8.5156. Min Act: -0.1700
Data Index: 997713 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5156. Min Range: -8.5156
Max Act: 8.4531. Min Act: -0.1700
Data Index: 7945058 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5156. Min Range: -8.5156
Max Act: 8.3906. Min Act: -0.1700
Data Index: 6176748 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5156. Min Range: -8.5156
Max Act: 8.3281. Min Act: -0.1700
Data Index: 2962962 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5156. Min Range: -8.5156
Max Act: 8.2656. Min Act: -0.1700
Data Index: 3189878 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5156. Min Range: -8.5156
Max Act: 8.2031. Min Act: -0.1700
Data Index: 7333493 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5156. Min Range: -8.5156
Max Act: 8.2031. Min Act: -0.1700
Data Index: 1782482 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5156. Min Range: -8.5156
Max Act: 8.2031. Min Act: -0.1700
Data Index: 7777814 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5156. Min Range: -8.5156
Max Act: 8.1406. Min Act: -0.1700
Data Index: 6581107 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5156. Min Range: -8.5156
Max Act: 8.1406. Min Act: -0.1700
Data Index: 1630475 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5156. Min Range: -8.5156
Max Act: 8.1406. Min Act: -0.1700
Data Index: 7890946 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5156. Min Range: -8.5156
Max Act: 8.0781. Min Act: -0.1700
Data Index: 6882667 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5156. Min Range: -8.5156
Max Act: 8.0781. Min Act: -0.1700
Data Index: 4990680 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5156. Min Range: -8.5156
Max Act: 8.1406. Min Act: -0.1700
Data Index: 1632503 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5156. Min Range: -8.5156
Max Act: 8.0781. Min Act: -0.1700
Data Index: 7257512 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5156. Min Range: -8.5156
Max Act: 8.0156. Min Act: -0.1700
Data Index: 680277 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5156. Min Range: -8.5156
Max Act: 8.0156. Min Act: -0.1700
Data Index: 2506591 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5156. Min Range: -8.5156
Max Act: 8.0156. Min Act: -0.1700
Data Index: 7568200 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5156. Min Range: -8.5156
Max Act: 7.9531. Min Act: -0.1700
Data Index: 6440876 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5156. Min Range: -8.5156
Max Act: 7.9531. Min Act: -0.1700
Data Index: 6038897 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #19