Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5893 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4281. Min Range: -6.4281
Max Act: 6.4281. Min Act: -0.1700
Data Index: 6184899 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4281. Min Range: -6.4281
Max Act: 5.8343. Min Act: -0.1700
Data Index: 27173 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4281. Min Range: -6.4281
Max Act: 5.8343. Min Act: -0.1700
Data Index: 727724 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4281. Min Range: -6.4281
Max Act: 5.8031. Min Act: -0.1700
Data Index: 8285806 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4281. Min Range: -6.4281
Max Act: 5.8031. Min Act: -0.1700
Data Index: 766395 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4281. Min Range: -6.4281
Max Act: 5.7718. Min Act: -0.1700
Data Index: 8105103 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4281. Min Range: -6.4281
Max Act: 5.7406. Min Act: -0.1700
Data Index: 3345700 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4281. Min Range: -6.4281
Max Act: 5.6781. Min Act: -0.1700
Data Index: 4904659 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4281. Min Range: -6.4281
Max Act: 5.7093. Min Act: -0.1700
Data Index: 4697702 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4281. Min Range: -6.4281
Max Act: 5.6781. Min Act: -0.1700
Data Index: 535240 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4281. Min Range: -6.4281
Max Act: 5.6468. Min Act: -0.1700
Data Index: 7765805 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4281. Min Range: -6.4281
Max Act: 5.6468. Min Act: -0.1700
Data Index: 6849438 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4281. Min Range: -6.4281
Max Act: 5.6468. Min Act: -0.1700
Data Index: 7124263 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4281. Min Range: -6.4281
Max Act: 5.6468. Min Act: -0.1700
Data Index: 28286 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4281. Min Range: -6.4281
Max Act: 5.6468. Min Act: -0.1700
Data Index: 1259638 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4281. Min Range: -6.4281
Max Act: 5.5843. Min Act: -0.1700
Data Index: 5858988 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4281. Min Range: -6.4281
Max Act: 5.6156. Min Act: -0.1700
Data Index: 2332976 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4281. Min Range: -6.4281
Max Act: 5.5843. Min Act: -0.1700
Data Index: 6090083 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4281. Min Range: -6.4281
Max Act: 5.6156. Min Act: -0.1700
Data Index: 8203436 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4281. Min Range: -6.4281
Max Act: 5.5843. Min Act: -0.1700
Data Index: 4785956 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #19