Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2806 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6551. Min Range: -7.6551
Max Act: 7.6551. Min Act: -0.1700
Data Index: 3803865 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6551. Min Range: -7.6551
Max Act: 7.5301. Min Act: -0.1700
Data Index: 4854289 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6551. Min Range: -7.6551
Max Act: 7.5301. Min Act: -0.1700
Data Index: 1198668 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6551. Min Range: -7.6551
Max Act: 7.4988. Min Act: -0.1700
Data Index: 7532797 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6551. Min Range: -7.6551
Max Act: 7.4988. Min Act: -0.1700
Data Index: 7727224 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6551. Min Range: -7.6551
Max Act: 7.4676. Min Act: -0.1700
Data Index: 1639519 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6551. Min Range: -7.6551
Max Act: 7.3738. Min Act: -0.1700
Data Index: 3929278 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6551. Min Range: -7.6551
Max Act: 7.4051. Min Act: -0.1700
Data Index: 9623 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6551. Min Range: -7.6551
Max Act: 7.3426. Min Act: -0.1700
Data Index: 5359937 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6551. Min Range: -7.6551
Max Act: 7.3113. Min Act: -0.1700
Data Index: 6268523 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6551. Min Range: -7.6551
Max Act: 7.3113. Min Act: -0.1700
Data Index: 250300 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6551. Min Range: -7.6551
Max Act: 7.3113. Min Act: -0.1700
Data Index: 6893529 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6551. Min Range: -7.6551
Max Act: 7.2801. Min Act: -0.1700
Data Index: 4565551 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6551. Min Range: -7.6551
Max Act: 7.2801. Min Act: -0.1700
Data Index: 8073256 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6551. Min Range: -7.6551
Max Act: 7.2176. Min Act: -0.1700
Data Index: 6096571 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6551. Min Range: -7.6551
Max Act: 7.1551. Min Act: -0.1700
Data Index: 8193028 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6551. Min Range: -7.6551
Max Act: 7.1551. Min Act: -0.1700
Data Index: 8187270 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6551. Min Range: -7.6551
Max Act: 7.1551. Min Act: -0.1700
Data Index: 711984 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6551. Min Range: -7.6551
Max Act: 7.1551. Min Act: -0.1700
Data Index: 7550232 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6551. Min Range: -7.6551
Max Act: 7.1551. Min Act: -0.1700
Data Index: 6299080 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #19