Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1644 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2978. Min Range: -5.2978
Max Act: 5.2978. Min Act: -0.1700
Data Index: 8704664 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2978. Min Range: -5.2978
Max Act: 5.2353. Min Act: -0.1700
Data Index: 8162550 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2978. Min Range: -5.2978
Max Act: 5.2353. Min Act: -0.1700
Data Index: 23490 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2978. Min Range: -5.2978
Max Act: 5.2353. Min Act: -0.1700
Data Index: 5995312 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2978. Min Range: -5.2978
Max Act: 5.2040. Min Act: -0.1700
Data Index: 2454606 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2978. Min Range: -5.2978
Max Act: 5.1728. Min Act: -0.1700
Data Index: 954773 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2978. Min Range: -5.2978
Max Act: 5.1415. Min Act: -0.1700
Data Index: 3257325 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2978. Min Range: -5.2978
Max Act: 5.1415. Min Act: -0.1700
Data Index: 8704461 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2978. Min Range: -5.2978
Max Act: 5.1415. Min Act: -0.1700
Data Index: 8157698 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2978. Min Range: -5.2978
Max Act: 5.1103. Min Act: -0.1700
Data Index: 5458668 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2978. Min Range: -5.2978
Max Act: 5.1103. Min Act: -0.1700
Data Index: 7142568 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2978. Min Range: -5.2978
Max Act: 5.0790. Min Act: -0.1700
Data Index: 4275207 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2978. Min Range: -5.2978
Max Act: 5.1103. Min Act: -0.1700
Data Index: 8691785 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2978. Min Range: -5.2978
Max Act: 5.1103. Min Act: -0.1700
Data Index: 8643988 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2978. Min Range: -5.2978
Max Act: 5.0790. Min Act: -0.1700
Data Index: 350070 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2978. Min Range: -5.2978
Max Act: 5.0790. Min Act: -0.1700
Data Index: 8044638 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2978. Min Range: -5.2978
Max Act: 5.0478. Min Act: -0.1700
Data Index: 5948590 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2978. Min Range: -5.2978
Max Act: 5.0790. Min Act: -0.1700
Data Index: 5196534 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2978. Min Range: -5.2978
Max Act: 5.0790. Min Act: -0.1700
Data Index: 6691815 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2978. Min Range: -5.2978
Max Act: 5.0478. Min Act: -0.1700
Data Index: 556003 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #19