Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2325 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2997. Min Range: -5.2997
Max Act: 5.2997. Min Act: -0.1700
Data Index: 3605052 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2997. Min Range: -5.2997
Max Act: 5.2060. Min Act: -0.1700
Data Index: 4235648 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2997. Min Range: -5.2997
Max Act: 5.2060. Min Act: -0.1700
Data Index: 2704487 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2997. Min Range: -5.2997
Max Act: 5.2372. Min Act: -0.1700
Data Index: 1113952 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2997. Min Range: -5.2997
Max Act: 5.1435. Min Act: -0.1700
Data Index: 4432917 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2997. Min Range: -5.2997
Max Act: 5.0810. Min Act: -0.1700
Data Index: 8686794 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2997. Min Range: -5.2997
Max Act: 5.0185. Min Act: -0.1700
Data Index: 6750195 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2997. Min Range: -5.2997
Max Act: 4.9872. Min Act: -0.1700
Data Index: 5925547 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2997. Min Range: -5.2997
Max Act: 4.9872. Min Act: -0.1700
Data Index: 3021394 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2997. Min Range: -5.2997
Max Act: 4.9560. Min Act: -0.1700
Data Index: 1764475 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2997. Min Range: -5.2997
Max Act: 4.9872. Min Act: -0.1700
Data Index: 1842850 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2997. Min Range: -5.2997
Max Act: 4.9247. Min Act: -0.1700
Data Index: 7550514 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2997. Min Range: -5.2997
Max Act: 4.9247. Min Act: -0.1700
Data Index: 4813064 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2997. Min Range: -5.2997
Max Act: 4.9247. Min Act: -0.1700
Data Index: 1427505 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2997. Min Range: -5.2997
Max Act: 4.9247. Min Act: -0.1700
Data Index: 6385982 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2997. Min Range: -5.2997
Max Act: 4.8935. Min Act: -0.1700
Data Index: 727435 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2997. Min Range: -5.2997
Max Act: 4.8622. Min Act: -0.1700
Data Index: 6766527 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2997. Min Range: -5.2997
Max Act: 4.8622. Min Act: -0.1700
Data Index: 789928 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2997. Min Range: -5.2997
Max Act: 4.8310. Min Act: -0.1700
Data Index: 6350520 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2997. Min Range: -5.2997
Max Act: 4.8310. Min Act: -0.1700
Data Index: 4695719 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #19