Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6066 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4324. Min Range: -7.4324
Max Act: 7.4324. Min Act: -0.1700
Data Index: 303565 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4324. Min Range: -7.4324
Max Act: 7.3699. Min Act: -0.1700
Data Index: 4992780 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4324. Min Range: -7.4324
Max Act: 7.3387. Min Act: -0.1700
Data Index: 179840 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4324. Min Range: -7.4324
Max Act: 7.3074. Min Act: -0.1700
Data Index: 2293398 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4324. Min Range: -7.4324
Max Act: 7.1512. Min Act: -0.1700
Data Index: 1692401 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4324. Min Range: -7.4324
Max Act: 7.1199. Min Act: -0.1700
Data Index: 5965500 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4324. Min Range: -7.4324
Max Act: 7.1199. Min Act: -0.1700
Data Index: 3522469 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4324. Min Range: -7.4324
Max Act: 7.0574. Min Act: -0.1700
Data Index: 220962 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4324. Min Range: -7.4324
Max Act: 7.0574. Min Act: -0.1700
Data Index: 6521468 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4324. Min Range: -7.4324
Max Act: 7.0574. Min Act: -0.1700
Data Index: 3510851 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4324. Min Range: -7.4324
Max Act: 7.0574. Min Act: -0.1700
Data Index: 3411265 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4324. Min Range: -7.4324
Max Act: 7.0574. Min Act: -0.1700
Data Index: 4468617 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4324. Min Range: -7.4324
Max Act: 7.0574. Min Act: -0.1700
Data Index: 4647291 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4324. Min Range: -7.4324
Max Act: 7.0262. Min Act: -0.1700
Data Index: 2912567 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4324. Min Range: -7.4324
Max Act: 6.9949. Min Act: -0.1700
Data Index: 8030295 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4324. Min Range: -7.4324
Max Act: 7.0262. Min Act: -0.1700
Data Index: 7872105 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4324. Min Range: -7.4324
Max Act: 6.9949. Min Act: -0.1700
Data Index: 4044836 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4324. Min Range: -7.4324
Max Act: 6.9637. Min Act: -0.1700
Data Index: 8260759 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4324. Min Range: -7.4324
Max Act: 6.9949. Min Act: -0.1700
Data Index: 647626 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4324. Min Range: -7.4324
Max Act: 6.9012. Min Act: -0.1700
Data Index: 3390040 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #19