Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 448 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4438. Min Range: -9.4438
Max Act: 9.3813. Min Act: -0.1700
Data Index: 6131972 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4438. Min Range: -9.4438
Max Act: 9.4438. Min Act: -0.1700
Data Index: 5898590 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4438. Min Range: -9.4438
Max Act: 9.3188. Min Act: -0.1700
Data Index: 2770457 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4438. Min Range: -9.4438
Max Act: 9.3188. Min Act: -0.1700
Data Index: 832224 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4438. Min Range: -9.4438
Max Act: 9.3188. Min Act: -0.1700
Data Index: 8274090 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4438. Min Range: -9.4438
Max Act: 9.3188. Min Act: -0.1700
Data Index: 8474907 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4438. Min Range: -9.4438
Max Act: 9.2563. Min Act: -0.1700
Data Index: 6222277 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4438. Min Range: -9.4438
Max Act: 9.2563. Min Act: -0.1700
Data Index: 4369025 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4438. Min Range: -9.4438
Max Act: 9.0688. Min Act: -0.1700
Data Index: 371539 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4438. Min Range: -9.4438
Max Act: 9.0688. Min Act: -0.1700
Data Index: 4212038 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4438. Min Range: -9.4438
Max Act: 9.0688. Min Act: -0.1700
Data Index: 6108353 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4438. Min Range: -9.4438
Max Act: 8.9438. Min Act: -0.1700
Data Index: 356798 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4438. Min Range: -9.4438
Max Act: 8.9438. Min Act: -0.1700
Data Index: 1781095 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4438. Min Range: -9.4438
Max Act: 8.8813. Min Act: -0.1700
Data Index: 2549898 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4438. Min Range: -9.4438
Max Act: 8.8813. Min Act: -0.1700
Data Index: 8390680 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4438. Min Range: -9.4438
Max Act: 8.8813. Min Act: -0.1700
Data Index: 7837262 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4438. Min Range: -9.4438
Max Act: 8.8188. Min Act: -0.1700
Data Index: 797707 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4438. Min Range: -9.4438
Max Act: 8.8188. Min Act: -0.1700
Data Index: 5936351 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4438. Min Range: -9.4438
Max Act: 8.8188. Min Act: -0.1700
Data Index: 1961037 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4438. Min Range: -9.4438
Max Act: 8.8188. Min Act: -0.1700
Data Index: 5470995 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #19