Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5392 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3649. Min Range: -7.3649
Max Act: 7.3649. Min Act: -0.1700
Data Index: 8213657 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3649. Min Range: -7.3649
Max Act: 7.0837. Min Act: -0.1700
Data Index: 5209476 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3649. Min Range: -7.3649
Max Act: 7.0524. Min Act: -0.1700
Data Index: 7801914 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3649. Min Range: -7.3649
Max Act: 6.9899. Min Act: -0.1700
Data Index: 6219444 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3649. Min Range: -7.3649
Max Act: 6.8649. Min Act: -0.1700
Data Index: 7795834 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3649. Min Range: -7.3649
Max Act: 6.8649. Min Act: -0.1700
Data Index: 4883536 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3649. Min Range: -7.3649
Max Act: 6.8337. Min Act: -0.1700
Data Index: 1661922 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3649. Min Range: -7.3649
Max Act: 6.8337. Min Act: -0.1700
Data Index: 4318474 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3649. Min Range: -7.3649
Max Act: 6.8649. Min Act: -0.1700
Data Index: 2472537 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3649. Min Range: -7.3649
Max Act: 6.8024. Min Act: -0.1700
Data Index: 1733211 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3649. Min Range: -7.3649
Max Act: 6.7087. Min Act: -0.1700
Data Index: 7317413 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3649. Min Range: -7.3649
Max Act: 6.7399. Min Act: -0.1700
Data Index: 1861250 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3649. Min Range: -7.3649
Max Act: 6.7399. Min Act: -0.1700
Data Index: 5443440 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3649. Min Range: -7.3649
Max Act: 6.7087. Min Act: -0.1700
Data Index: 5492312 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3649. Min Range: -7.3649
Max Act: 6.6774. Min Act: -0.1700
Data Index: 3142793 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3649. Min Range: -7.3649
Max Act: 6.6774. Min Act: -0.1700
Data Index: 5754787 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3649. Min Range: -7.3649
Max Act: 6.6149. Min Act: -0.1700
Data Index: 4550346 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3649. Min Range: -7.3649
Max Act: 6.6462. Min Act: -0.1700
Data Index: 5889978 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3649. Min Range: -7.3649
Max Act: 6.6149. Min Act: -0.1700
Data Index: 3694929 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3649. Min Range: -7.3649
Max Act: 6.5837. Min Act: -0.1700
Data Index: 5453986 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #19