Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3697 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8468. Min Range: -3.8468
Max Act: 3.8468. Min Act: -0.1700
Data Index: 1793600 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8468. Min Range: -3.8468
Max Act: 3.8155. Min Act: -0.1700
Data Index: 8259998 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8468. Min Range: -3.8468
Max Act: 3.6904. Min Act: -0.1700
Data Index: 8068657 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8468. Min Range: -3.8468
Max Act: 3.5809. Min Act: -0.1700
Data Index: 4460303 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8468. Min Range: -3.8468
Max Act: 3.5965. Min Act: -0.1700
Data Index: 8259992 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8468. Min Range: -3.8468
Max Act: 3.5026. Min Act: -0.1700
Data Index: 1535868 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8468. Min Range: -3.8468
Max Act: 3.5026. Min Act: -0.1700
Data Index: 3190775 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8468. Min Range: -3.8468
Max Act: 3.5026. Min Act: -0.1700
Data Index: 3971744 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8468. Min Range: -3.8468
Max Act: 3.4869. Min Act: -0.1700
Data Index: 1349107 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8468. Min Range: -3.8468
Max Act: 3.4869. Min Act: -0.1700
Data Index: 8239267 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8468. Min Range: -3.8468
Max Act: 3.4712. Min Act: -0.1700
Data Index: 6411495 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8468. Min Range: -3.8468
Max Act: 3.4712. Min Act: -0.1700
Data Index: 2886640 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8468. Min Range: -3.8468
Max Act: 3.4556. Min Act: -0.1700
Data Index: 6712954 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8468. Min Range: -3.8468
Max Act: 3.4399. Min Act: -0.1700
Data Index: 5723620 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8468. Min Range: -3.8468
Max Act: 3.4399. Min Act: -0.1700
Data Index: 4825197 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8468. Min Range: -3.8468
Max Act: 3.4399. Min Act: -0.1700
Data Index: 8824299 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8468. Min Range: -3.8468
Max Act: 3.4242. Min Act: -0.1700
Data Index: 658061 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8468. Min Range: -3.8468
Max Act: 3.4556. Min Act: -0.1700
Data Index: 8068660 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8468. Min Range: -3.8468
Max Act: 3.4086. Min Act: -0.1700
Data Index: 4373499 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8468. Min Range: -3.8468
Max Act: 3.4242. Min Act: -0.1700
Data Index: 2150596 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #19