Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3607 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4361. Min Range: -4.4361
Max Act: 4.4361. Min Act: -0.1700
Data Index: 1956650 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4361. Min Range: -4.4361
Max Act: 4.1236. Min Act: -0.1700
Data Index: 966804 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4361. Min Range: -4.4361
Max Act: 3.9986. Min Act: -0.1700
Data Index: 338720 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4361. Min Range: -4.4361
Max Act: 3.9986. Min Act: -0.1700
Data Index: 1553700 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4361. Min Range: -4.4361
Max Act: 3.9986. Min Act: -0.1700
Data Index: 8008416 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4361. Min Range: -4.4361
Max Act: 3.9986. Min Act: -0.1700
Data Index: 6080097 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4361. Min Range: -4.4361
Max Act: 3.9673. Min Act: -0.1700
Data Index: 119443 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4361. Min Range: -4.4361
Max Act: 3.9673. Min Act: -0.1700
Data Index: 1727233 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4361. Min Range: -4.4361
Max Act: 3.9673. Min Act: -0.1700
Data Index: 4686313 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4361. Min Range: -4.4361
Max Act: 3.9673. Min Act: -0.1700
Data Index: 156794 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4361. Min Range: -4.4361
Max Act: 3.9673. Min Act: -0.1700
Data Index: 8604364 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4361. Min Range: -4.4361
Max Act: 3.9673. Min Act: -0.1700
Data Index: 8522699 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4361. Min Range: -4.4361
Max Act: 3.9673. Min Act: -0.1700
Data Index: 8033242 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4361. Min Range: -4.4361
Max Act: 3.9673. Min Act: -0.1700
Data Index: 5149450 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4361. Min Range: -4.4361
Max Act: 3.9360. Min Act: -0.1700
Data Index: 4352695 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4361. Min Range: -4.4361
Max Act: 3.9360. Min Act: -0.1700
Data Index: 4389812 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4361. Min Range: -4.4361
Max Act: 3.9360. Min Act: -0.1700
Data Index: 2677969 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4361. Min Range: -4.4361
Max Act: 3.9360. Min Act: -0.1700
Data Index: 3832584 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4361. Min Range: -4.4361
Max Act: 3.9360. Min Act: -0.1700
Data Index: 6902278 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4361. Min Range: -4.4361
Max Act: 3.9360. Min Act: -0.1700
Data Index: 6909908 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #19