Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2738 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4136. Min Range: -7.4136
Max Act: 7.4136. Min Act: -0.1700
Data Index: 8717414 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4136. Min Range: -7.4136
Max Act: 7.1948. Min Act: -0.1700
Data Index: 7928657 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4136. Min Range: -7.4136
Max Act: 6.9448. Min Act: -0.1700
Data Index: 3940857 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4136. Min Range: -7.4136
Max Act: 6.8823. Min Act: -0.1700
Data Index: 4852279 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4136. Min Range: -7.4136
Max Act: 6.8198. Min Act: -0.1700
Data Index: 1567780 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4136. Min Range: -7.4136
Max Act: 6.6636. Min Act: -0.1700
Data Index: 5158303 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4136. Min Range: -7.4136
Max Act: 6.6636. Min Act: -0.1700
Data Index: 125415 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4136. Min Range: -7.4136
Max Act: 6.6636. Min Act: -0.1700
Data Index: 3907224 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4136. Min Range: -7.4136
Max Act: 6.6323. Min Act: -0.1700
Data Index: 3053406 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4136. Min Range: -7.4136
Max Act: 6.6323. Min Act: -0.1700
Data Index: 3940865 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4136. Min Range: -7.4136
Max Act: 6.6323. Min Act: -0.1700
Data Index: 3504800 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4136. Min Range: -7.4136
Max Act: 6.6011. Min Act: -0.1700
Data Index: 5410653 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4136. Min Range: -7.4136
Max Act: 6.6323. Min Act: -0.1700
Data Index: 7158429 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4136. Min Range: -7.4136
Max Act: 6.5698. Min Act: -0.1700
Data Index: 3315548 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4136. Min Range: -7.4136
Max Act: 6.5698. Min Act: -0.1700
Data Index: 172518 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4136. Min Range: -7.4136
Max Act: 6.5698. Min Act: -0.1700
Data Index: 4218032 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4136. Min Range: -7.4136
Max Act: 6.5386. Min Act: -0.1700
Data Index: 7282364 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4136. Min Range: -7.4136
Max Act: 6.5073. Min Act: -0.1700
Data Index: 12907 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4136. Min Range: -7.4136
Max Act: 6.4761. Min Act: -0.1700
Data Index: 4257812 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4136. Min Range: -7.4136
Max Act: 6.4761. Min Act: -0.1700
Data Index: 3368336 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #19