Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3440 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2325. Min Range: -9.2325
Max Act: 9.2325. Min Act: -0.1700
Data Index: 6829215 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2325. Min Range: -9.2325
Max Act: 8.8575. Min Act: -0.1700
Data Index: 7690676 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2325. Min Range: -9.2325
Max Act: 8.6700. Min Act: -0.1700
Data Index: 7963588 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2325. Min Range: -9.2325
Max Act: 8.4825. Min Act: -0.1700
Data Index: 1175742 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2325. Min Range: -9.2325
Max Act: 8.4200. Min Act: -0.1700
Data Index: 3616917 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2325. Min Range: -9.2325
Max Act: 8.4200. Min Act: -0.1700
Data Index: 3326262 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2325. Min Range: -9.2325
Max Act: 8.3575. Min Act: -0.1700
Data Index: 8538919 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2325. Min Range: -9.2325
Max Act: 8.2950. Min Act: -0.1700
Data Index: 5669794 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2325. Min Range: -9.2325
Max Act: 8.2950. Min Act: -0.1700
Data Index: 865104 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2325. Min Range: -9.2325
Max Act: 8.2325. Min Act: -0.1700
Data Index: 4788398 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2325. Min Range: -9.2325
Max Act: 8.2325. Min Act: -0.1700
Data Index: 1234684 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2325. Min Range: -9.2325
Max Act: 8.1700. Min Act: -0.1700
Data Index: 3604300 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2325. Min Range: -9.2325
Max Act: 8.1700. Min Act: -0.1700
Data Index: 2219628 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2325. Min Range: -9.2325
Max Act: 8.1700. Min Act: -0.1700
Data Index: 70667 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2325. Min Range: -9.2325
Max Act: 8.1700. Min Act: -0.1700
Data Index: 5812971 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2325. Min Range: -9.2325
Max Act: 8.1075. Min Act: -0.1700
Data Index: 6416406 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2325. Min Range: -9.2325
Max Act: 8.1075. Min Act: -0.1700
Data Index: 6232539 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2325. Min Range: -9.2325
Max Act: 8.0450. Min Act: -0.1700
Data Index: 1328788 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2325. Min Range: -9.2325
Max Act: 8.0450. Min Act: -0.1700
Data Index: 1698767 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2325. Min Range: -9.2325
Max Act: 8.0450. Min Act: -0.1700
Data Index: 1756475 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #19