Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3510 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6596. Min Range: -7.6596
Max Act: 7.6596. Min Act: -0.1700
Data Index: 6704689 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6596. Min Range: -7.6596
Max Act: 7.5346. Min Act: -0.1700
Data Index: 5868987 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6596. Min Range: -7.6596
Max Act: 7.4721. Min Act: -0.1700
Data Index: 7451116 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6596. Min Range: -7.6596
Max Act: 7.3158. Min Act: -0.1700
Data Index: 7700396 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6596. Min Range: -7.6596
Max Act: 7.2846. Min Act: -0.1700
Data Index: 1886877 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6596. Min Range: -7.6596
Max Act: 7.2221. Min Act: -0.1700
Data Index: 4961566 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6596. Min Range: -7.6596
Max Act: 7.2533. Min Act: -0.1700
Data Index: 6132445 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6596. Min Range: -7.6596
Max Act: 7.2221. Min Act: -0.1700
Data Index: 5091805 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6596. Min Range: -7.6596
Max Act: 7.1283. Min Act: -0.1700
Data Index: 1139733 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6596. Min Range: -7.6596
Max Act: 7.0971. Min Act: -0.1700
Data Index: 7951273 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6596. Min Range: -7.6596
Max Act: 7.0971. Min Act: -0.1700
Data Index: 8200549 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6596. Min Range: -7.6596
Max Act: 7.0971. Min Act: -0.1700
Data Index: 2722506 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6596. Min Range: -7.6596
Max Act: 6.9096. Min Act: -0.1700
Data Index: 7455676 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6596. Min Range: -7.6596
Max Act: 6.9408. Min Act: -0.1700
Data Index: 3478435 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6596. Min Range: -7.6596
Max Act: 6.9721. Min Act: -0.1700
Data Index: 8392014 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6596. Min Range: -7.6596
Max Act: 6.9096. Min Act: -0.1700
Data Index: 1661772 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6596. Min Range: -7.6596
Max Act: 6.9096. Min Act: -0.1700
Data Index: 1515861 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6596. Min Range: -7.6596
Max Act: 6.8783. Min Act: -0.1700
Data Index: 6673562 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6596. Min Range: -7.6596
Max Act: 6.8471. Min Act: -0.1700
Data Index: 6449086 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6596. Min Range: -7.6596
Max Act: 6.8471. Min Act: -0.1700
Data Index: 4898509 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #19