Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3648 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5596. Min Range: -6.5596
Max Act: 6.5596. Min Act: -0.1700
Data Index: 7324998 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5596. Min Range: -6.5596
Max Act: 6.2158. Min Act: -0.1700
Data Index: 1229893 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5596. Min Range: -6.5596
Max Act: 6.1533. Min Act: -0.1700
Data Index: 7563748 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5596. Min Range: -6.5596
Max Act: 6.1533. Min Act: -0.1700
Data Index: 1456755 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5596. Min Range: -6.5596
Max Act: 6.0283. Min Act: -0.1700
Data Index: 334484 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5596. Min Range: -6.5596
Max Act: 5.9971. Min Act: -0.1700
Data Index: 190448 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5596. Min Range: -6.5596
Max Act: 5.9346. Min Act: -0.1700
Data Index: 895366 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5596. Min Range: -6.5596
Max Act: 5.6846. Min Act: -0.1700
Data Index: 6999172 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5596. Min Range: -6.5596
Max Act: 5.6846. Min Act: -0.1700
Data Index: 656239 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5596. Min Range: -6.5596
Max Act: 5.6533. Min Act: -0.1700
Data Index: 8749124 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5596. Min Range: -6.5596
Max Act: 5.6533. Min Act: -0.1700
Data Index: 5633784 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5596. Min Range: -6.5596
Max Act: 5.6533. Min Act: -0.1700
Data Index: 1026725 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5596. Min Range: -6.5596
Max Act: 5.5908. Min Act: -0.1700
Data Index: 419659 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5596. Min Range: -6.5596
Max Act: 5.5283. Min Act: -0.1700
Data Index: 7409799 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5596. Min Range: -6.5596
Max Act: 5.5283. Min Act: -0.1700
Data Index: 8349995 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5596. Min Range: -6.5596
Max Act: 5.4971. Min Act: -0.1700
Data Index: 4644719 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5596. Min Range: -6.5596
Max Act: 5.4971. Min Act: -0.1700
Data Index: 4590984 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5596. Min Range: -6.5596
Max Act: 5.4971. Min Act: -0.1700
Data Index: 346603 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5596. Min Range: -6.5596
Max Act: 5.4658. Min Act: -0.1700
Data Index: 6416827 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5596. Min Range: -6.5596
Max Act: 5.4971. Min Act: -0.1700
Data Index: 6535139 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #19