Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1523 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.5430. Min Range: -2.5430
Max Act: 2.5430. Min Act: -0.1700
Data Index: 1358968 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5430. Min Range: -2.5430
Max Act: 2.4782. Min Act: -0.1700
Data Index: 1402772 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5430. Min Range: -2.5430
Max Act: 2.4131. Min Act: -0.1700
Data Index: 7826353 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5430. Min Range: -2.5430
Max Act: 2.4457. Min Act: -0.1700
Data Index: 2006447 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5430. Min Range: -2.5430
Max Act: 2.3478. Min Act: -0.1700
Data Index: 5634471 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5430. Min Range: -2.5430
Max Act: 2.3805. Min Act: -0.1700
Data Index: 2652781 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5430. Min Range: -2.5430
Max Act: 2.3641. Min Act: -0.1700
Data Index: 5143953 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5430. Min Range: -2.5430
Max Act: 2.3641. Min Act: -0.1700
Data Index: 8187806 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5430. Min Range: -2.5430
Max Act: 2.3805. Min Act: -0.1700
Data Index: 7552010 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5430. Min Range: -2.5430
Max Act: 2.4294. Min Act: -0.1700
Data Index: 4489131 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5430. Min Range: -2.5430
Max Act: 2.3968. Min Act: -0.1700
Data Index: 2368132 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5430. Min Range: -2.5430
Max Act: 2.3641. Min Act: -0.1700
Data Index: 1524282 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5430. Min Range: -2.5430
Max Act: 2.3641. Min Act: -0.1700
Data Index: 617990 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5430. Min Range: -2.5430
Max Act: 2.3641. Min Act: -0.1700
Data Index: 3342609 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5430. Min Range: -2.5430
Max Act: 2.3478. Min Act: -0.1700
Data Index: 5024474 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5430. Min Range: -2.5430
Max Act: 2.3314. Min Act: -0.1700
Data Index: 4548047 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5430. Min Range: -2.5430
Max Act: 2.3641. Min Act: -0.1700
Data Index: 7116133 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5430. Min Range: -2.5430
Max Act: 2.2985. Min Act: -0.1700
Data Index: 6439484 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5430. Min Range: -2.5430
Max Act: 2.2985. Min Act: -0.1700
Data Index: 483233 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5430. Min Range: -2.5430
Max Act: 2.3149. Min Act: -0.1700
Data Index: 2200891 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #19