Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 274 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8887. Min Range: -4.8887
Max Act: 4.8887. Min Act: -0.1700
Data Index: 2023689 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8887. Min Range: -4.8887
Max Act: 4.8262. Min Act: -0.1700
Data Index: 2849359 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8887. Min Range: -4.8887
Max Act: 4.7950. Min Act: -0.1700
Data Index: 443175 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8887. Min Range: -4.8887
Max Act: 4.7637. Min Act: -0.1700
Data Index: 1358550 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8887. Min Range: -4.8887
Max Act: 4.7950. Min Act: -0.1700
Data Index: 6815725 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8887. Min Range: -4.8887
Max Act: 4.7325. Min Act: -0.1700
Data Index: 2306619 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8887. Min Range: -4.8887
Max Act: 4.7012. Min Act: -0.1700
Data Index: 7523468 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8887. Min Range: -4.8887
Max Act: 4.6700. Min Act: -0.1700
Data Index: 4567537 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8887. Min Range: -4.8887
Max Act: 4.6387. Min Act: -0.1700
Data Index: 5914815 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8887. Min Range: -4.8887
Max Act: 4.5762. Min Act: -0.1700
Data Index: 3795479 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8887. Min Range: -4.8887
Max Act: 4.5762. Min Act: -0.1700
Data Index: 757521 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8887. Min Range: -4.8887
Max Act: 4.5762. Min Act: -0.1700
Data Index: 8111456 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8887. Min Range: -4.8887
Max Act: 4.5762. Min Act: -0.1700
Data Index: 4663190 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8887. Min Range: -4.8887
Max Act: 4.5762. Min Act: -0.1700
Data Index: 2578018 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8887. Min Range: -4.8887
Max Act: 4.5450. Min Act: -0.1700
Data Index: 2810046 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8887. Min Range: -4.8887
Max Act: 4.5450. Min Act: -0.1700
Data Index: 4362060 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8887. Min Range: -4.8887
Max Act: 4.5450. Min Act: -0.1700
Data Index: 692876 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8887. Min Range: -4.8887
Max Act: 4.5137. Min Act: -0.1700
Data Index: 8273425 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8887. Min Range: -4.8887
Max Act: 4.4825. Min Act: -0.1700
Data Index: 3882086 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8887. Min Range: -4.8887
Max Act: 4.4825. Min Act: -0.1700
Data Index: 5708279 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #19