Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5666 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2762. Min Range: -6.2762
Max Act: 6.2762. Min Act: -0.1700
Data Index: 1694104 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2762. Min Range: -6.2762
Max Act: 6.0887. Min Act: -0.1700
Data Index: 5997617 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2762. Min Range: -6.2762
Max Act: 6.0262. Min Act: -0.1700
Data Index: 4795652 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2762. Min Range: -6.2762
Max Act: 6.0262. Min Act: -0.1700
Data Index: 6412697 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2762. Min Range: -6.2762
Max Act: 5.9637. Min Act: -0.1700
Data Index: 2346117 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2762. Min Range: -6.2762
Max Act: 5.9637. Min Act: -0.1700
Data Index: 5310513 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2762. Min Range: -6.2762
Max Act: 5.9637. Min Act: -0.1700
Data Index: 3005014 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2762. Min Range: -6.2762
Max Act: 5.9325. Min Act: -0.1700
Data Index: 2957358 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2762. Min Range: -6.2762
Max Act: 5.9637. Min Act: -0.1700
Data Index: 3101107 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2762. Min Range: -6.2762
Max Act: 5.9325. Min Act: -0.1700
Data Index: 2346116 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2762. Min Range: -6.2762
Max Act: 5.9325. Min Act: -0.1700
Data Index: 2417476 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2762. Min Range: -6.2762
Max Act: 5.9012. Min Act: -0.1700
Data Index: 2003888 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2762. Min Range: -6.2762
Max Act: 5.9012. Min Act: -0.1700
Data Index: 8742786 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2762. Min Range: -6.2762
Max Act: 5.9012. Min Act: -0.1700
Data Index: 7853348 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2762. Min Range: -6.2762
Max Act: 5.9012. Min Act: -0.1700
Data Index: 6784595 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2762. Min Range: -6.2762
Max Act: 5.9012. Min Act: -0.1700
Data Index: 3101105 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2762. Min Range: -6.2762
Max Act: 5.8700. Min Act: -0.1700
Data Index: 8271771 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2762. Min Range: -6.2762
Max Act: 5.8700. Min Act: -0.1700
Data Index: 796617 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2762. Min Range: -6.2762
Max Act: 5.8700. Min Act: -0.1700
Data Index: 30689 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2762. Min Range: -6.2762
Max Act: 5.8387. Min Act: -0.1700
Data Index: 7894525 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #19