Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3899 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1156. Min Range: -5.1156
Max Act: 5.1156. Min Act: -0.1700
Data Index: 2828907 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1156. Min Range: -5.1156
Max Act: 5.0843. Min Act: -0.1700
Data Index: 1172525 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1156. Min Range: -5.1156
Max Act: 5.1156. Min Act: -0.1700
Data Index: 7070986 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1156. Min Range: -5.1156
Max Act: 4.9593. Min Act: -0.1700
Data Index: 7116850 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1156. Min Range: -5.1156
Max Act: 4.8656. Min Act: -0.1700
Data Index: 1574227 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1156. Min Range: -5.1156
Max Act: 4.8343. Min Act: -0.1700
Data Index: 1048356 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1156. Min Range: -5.1156
Max Act: 4.8343. Min Act: -0.1700
Data Index: 1589224 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1156. Min Range: -5.1156
Max Act: 4.8031. Min Act: -0.1700
Data Index: 6330071 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1156. Min Range: -5.1156
Max Act: 4.7406. Min Act: -0.1700
Data Index: 6414795 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1156. Min Range: -5.1156
Max Act: 4.7718. Min Act: -0.1700
Data Index: 4329305 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1156. Min Range: -5.1156
Max Act: 4.7718. Min Act: -0.1700
Data Index: 3297731 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1156. Min Range: -5.1156
Max Act: 4.7718. Min Act: -0.1700
Data Index: 737294 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1156. Min Range: -5.1156
Max Act: 4.7406. Min Act: -0.1700
Data Index: 536268 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1156. Min Range: -5.1156
Max Act: 4.7406. Min Act: -0.1700
Data Index: 3576937 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1156. Min Range: -5.1156
Max Act: 4.7406. Min Act: -0.1700
Data Index: 6713408 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1156. Min Range: -5.1156
Max Act: 4.7718. Min Act: -0.1700
Data Index: 8025012 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1156. Min Range: -5.1156
Max Act: 4.7093. Min Act: -0.1700
Data Index: 2560411 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1156. Min Range: -5.1156
Max Act: 4.7093. Min Act: -0.1700
Data Index: 81294 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1156. Min Range: -5.1156
Max Act: 4.7093. Min Act: -0.1700
Data Index: 530665 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1156. Min Range: -5.1156
Max Act: 4.7093. Min Act: -0.1700
Data Index: 5332637 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #19