Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1800 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2384. Min Range: -8.2384
Max Act: 8.2384. Min Act: -0.1700
Data Index: 8543068 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2384. Min Range: -8.2384
Max Act: 8.0509. Min Act: -0.1700
Data Index: 1472222 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2384. Min Range: -8.2384
Max Act: 7.9884. Min Act: -0.1700
Data Index: 5316618 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2384. Min Range: -8.2384
Max Act: 7.8634. Min Act: -0.1700
Data Index: 608581 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2384. Min Range: -8.2384
Max Act: 7.8009. Min Act: -0.1700
Data Index: 5532308 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2384. Min Range: -8.2384
Max Act: 7.8009. Min Act: -0.1700
Data Index: 428756 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2384. Min Range: -8.2384
Max Act: 7.8009. Min Act: -0.1700
Data Index: 8054370 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2384. Min Range: -8.2384
Max Act: 7.8009. Min Act: -0.1700
Data Index: 3244814 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2384. Min Range: -8.2384
Max Act: 7.7384. Min Act: -0.1700
Data Index: 3613696 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2384. Min Range: -8.2384
Max Act: 7.7384. Min Act: -0.1700
Data Index: 6597365 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2384. Min Range: -8.2384
Max Act: 7.7384. Min Act: -0.1700
Data Index: 7855445 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2384. Min Range: -8.2384
Max Act: 7.7384. Min Act: -0.1700
Data Index: 3143374 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2384. Min Range: -8.2384
Max Act: 7.7384. Min Act: -0.1700
Data Index: 4390377 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2384. Min Range: -8.2384
Max Act: 7.6759. Min Act: -0.1700
Data Index: 5336153 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2384. Min Range: -8.2384
Max Act: 7.6759. Min Act: -0.1700
Data Index: 7942652 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2384. Min Range: -8.2384
Max Act: 7.6759. Min Act: -0.1700
Data Index: 2308662 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2384. Min Range: -8.2384
Max Act: 7.6759. Min Act: -0.1700
Data Index: 6525573 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2384. Min Range: -8.2384
Max Act: 7.6134. Min Act: -0.1700
Data Index: 1485287 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2384. Min Range: -8.2384
Max Act: 7.6134. Min Act: -0.1700
Data Index: 2436317 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2384. Min Range: -8.2384
Max Act: 7.6134. Min Act: -0.1700
Data Index: 4476076 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #19