Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3340 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6325. Min Range: -7.6325
Max Act: 7.6325. Min Act: -0.1700
Data Index: 3744378 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6325. Min Range: -7.6325
Max Act: 7.5700. Min Act: -0.1700
Data Index: 4789892 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6325. Min Range: -7.6325
Max Act: 7.5700. Min Act: -0.1700
Data Index: 3577220 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6325. Min Range: -7.6325
Max Act: 7.3825. Min Act: -0.1700
Data Index: 5901549 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6325. Min Range: -7.6325
Max Act: 7.4137. Min Act: -0.1700
Data Index: 3947680 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6325. Min Range: -7.6325
Max Act: 7.4137. Min Act: -0.1700
Data Index: 2718174 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6325. Min Range: -7.6325
Max Act: 7.3512. Min Act: -0.1700
Data Index: 1958926 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6325. Min Range: -7.6325
Max Act: 7.3200. Min Act: -0.1700
Data Index: 258133 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6325. Min Range: -7.6325
Max Act: 7.2575. Min Act: -0.1700
Data Index: 7056893 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6325. Min Range: -7.6325
Max Act: 7.2262. Min Act: -0.1700
Data Index: 377442 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6325. Min Range: -7.6325
Max Act: 7.2575. Min Act: -0.1700
Data Index: 436481 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6325. Min Range: -7.6325
Max Act: 7.2262. Min Act: -0.1700
Data Index: 7129902 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6325. Min Range: -7.6325
Max Act: 7.1950. Min Act: -0.1700
Data Index: 1480048 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6325. Min Range: -7.6325
Max Act: 7.1950. Min Act: -0.1700
Data Index: 2069336 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6325. Min Range: -7.6325
Max Act: 7.1637. Min Act: -0.1700
Data Index: 3375344 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6325. Min Range: -7.6325
Max Act: 7.1637. Min Act: -0.1700
Data Index: 944992 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6325. Min Range: -7.6325
Max Act: 7.1637. Min Act: -0.1700
Data Index: 8677100 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6325. Min Range: -7.6325
Max Act: 7.1325. Min Act: -0.1700
Data Index: 3272651 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6325. Min Range: -7.6325
Max Act: 7.1637. Min Act: -0.1700
Data Index: 7033258 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6325. Min Range: -7.6325
Max Act: 7.1325. Min Act: -0.1700
Data Index: 3817500 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #19