Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3014 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7512. Min Range: -6.7512
Max Act: 6.7512. Min Act: -0.1700
Data Index: 5537401 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7512. Min Range: -6.7512
Max Act: 6.6262. Min Act: -0.1700
Data Index: 5343149 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7512. Min Range: -6.7512
Max Act: 6.5637. Min Act: -0.1700
Data Index: 6572204 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7512. Min Range: -6.7512
Max Act: 6.4700. Min Act: -0.1700
Data Index: 5555704 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7512. Min Range: -6.7512
Max Act: 6.5012. Min Act: -0.1700
Data Index: 7524369 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7512. Min Range: -6.7512
Max Act: 6.4387. Min Act: -0.1700
Data Index: 8017971 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7512. Min Range: -6.7512
Max Act: 6.4075. Min Act: -0.1700
Data Index: 7700307 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7512. Min Range: -6.7512
Max Act: 6.4075. Min Act: -0.1700
Data Index: 8370142 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7512. Min Range: -6.7512
Max Act: 6.4075. Min Act: -0.1700
Data Index: 980877 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7512. Min Range: -6.7512
Max Act: 6.3762. Min Act: -0.1700
Data Index: 6065927 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7512. Min Range: -6.7512
Max Act: 6.3762. Min Act: -0.1700
Data Index: 140842 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7512. Min Range: -6.7512
Max Act: 6.3137. Min Act: -0.1700
Data Index: 5531741 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7512. Min Range: -6.7512
Max Act: 6.2825. Min Act: -0.1700
Data Index: 766547 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7512. Min Range: -6.7512
Max Act: 6.2825. Min Act: -0.1700
Data Index: 1568768 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7512. Min Range: -6.7512
Max Act: 6.3137. Min Act: -0.1700
Data Index: 2561432 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7512. Min Range: -6.7512
Max Act: 6.2825. Min Act: -0.1700
Data Index: 3234690 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7512. Min Range: -6.7512
Max Act: 6.2825. Min Act: -0.1700
Data Index: 1209345 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7512. Min Range: -6.7512
Max Act: 6.2825. Min Act: -0.1700
Data Index: 3654859 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7512. Min Range: -6.7512
Max Act: 6.2825. Min Act: -0.1700
Data Index: 3045488 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7512. Min Range: -6.7512
Max Act: 6.2200. Min Act: -0.1700
Data Index: 4184378 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #19