Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4321 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3346. Min Range: -7.3346
Max Act: 7.3346. Min Act: -0.1700
Data Index: 3905372 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3346. Min Range: -7.3346
Max Act: 7.0846. Min Act: -0.1700
Data Index: 1109109 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3346. Min Range: -7.3346
Max Act: 7.0221. Min Act: -0.1700
Data Index: 528781 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3346. Min Range: -7.3346
Max Act: 7.0221. Min Act: -0.1700
Data Index: 5008527 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3346. Min Range: -7.3346
Max Act: 6.9909. Min Act: -0.1700
Data Index: 791397 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3346. Min Range: -7.3346
Max Act: 6.9909. Min Act: -0.1700
Data Index: 8248621 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3346. Min Range: -7.3346
Max Act: 6.9909. Min Act: -0.1700
Data Index: 4938431 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3346. Min Range: -7.3346
Max Act: 6.9909. Min Act: -0.1700
Data Index: 4129408 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3346. Min Range: -7.3346
Max Act: 6.9596. Min Act: -0.1700
Data Index: 7609606 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3346. Min Range: -7.3346
Max Act: 6.9284. Min Act: -0.1700
Data Index: 7079504 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3346. Min Range: -7.3346
Max Act: 6.8971. Min Act: -0.1700
Data Index: 7385786 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3346. Min Range: -7.3346
Max Act: 6.8659. Min Act: -0.1700
Data Index: 2410211 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3346. Min Range: -7.3346
Max Act: 6.8659. Min Act: -0.1700
Data Index: 584861 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3346. Min Range: -7.3346
Max Act: 6.8346. Min Act: -0.1700
Data Index: 1291185 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3346. Min Range: -7.3346
Max Act: 6.8034. Min Act: -0.1700
Data Index: 7126528 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3346. Min Range: -7.3346
Max Act: 6.8346. Min Act: -0.1700
Data Index: 3628503 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3346. Min Range: -7.3346
Max Act: 6.8346. Min Act: -0.1700
Data Index: 3964276 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3346. Min Range: -7.3346
Max Act: 6.8346. Min Act: -0.1700
Data Index: 5154063 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3346. Min Range: -7.3346
Max Act: 6.8346. Min Act: -0.1700
Data Index: 1397413 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3346. Min Range: -7.3346
Max Act: 6.8034. Min Act: -0.1700
Data Index: 169572 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #19