Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2851 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2675. Min Range: -5.2675
Max Act: 5.2363. Min Act: -0.1700
Data Index: 8152659 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2675. Min Range: -5.2675
Max Act: 5.2363. Min Act: -0.1700
Data Index: 1556849 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2675. Min Range: -5.2675
Max Act: 5.2675. Min Act: -0.1700
Data Index: 1762948 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2675. Min Range: -5.2675
Max Act: 5.1425. Min Act: -0.1700
Data Index: 6008874 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2675. Min Range: -5.2675
Max Act: 5.1738. Min Act: -0.1700
Data Index: 1040629 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2675. Min Range: -5.2675
Max Act: 5.1113. Min Act: -0.1700
Data Index: 1573644 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2675. Min Range: -5.2675
Max Act: 5.0488. Min Act: -0.1700
Data Index: 4513227 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2675. Min Range: -5.2675
Max Act: 5.0800. Min Act: -0.1700
Data Index: 6541501 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2675. Min Range: -5.2675
Max Act: 5.0800. Min Act: -0.1700
Data Index: 7510878 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2675. Min Range: -5.2675
Max Act: 5.0800. Min Act: -0.1700
Data Index: 2791939 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2675. Min Range: -5.2675
Max Act: 5.0800. Min Act: -0.1700
Data Index: 848612 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2675. Min Range: -5.2675
Max Act: 5.0800. Min Act: -0.1700
Data Index: 1300376 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2675. Min Range: -5.2675
Max Act: 5.0488. Min Act: -0.1700
Data Index: 2545789 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2675. Min Range: -5.2675
Max Act: 5.0488. Min Act: -0.1700
Data Index: 6796568 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2675. Min Range: -5.2675
Max Act: 5.0488. Min Act: -0.1700
Data Index: 6448078 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2675. Min Range: -5.2675
Max Act: 5.0488. Min Act: -0.1700
Data Index: 1779436 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2675. Min Range: -5.2675
Max Act: 5.0175. Min Act: -0.1700
Data Index: 6008879 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2675. Min Range: -5.2675
Max Act: 4.9863. Min Act: -0.1700
Data Index: 1470938 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2675. Min Range: -5.2675
Max Act: 4.9863. Min Act: -0.1700
Data Index: 6840254 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2675. Min Range: -5.2675
Max Act: 4.9863. Min Act: -0.1700
Data Index: 5766676 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #19