Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6394 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7504. Min Range: -2.7504
Max Act: 2.7504. Min Act: -0.1700
Data Index: 6213654 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7504. Min Range: -2.7504
Max Act: 2.6864. Min Act: -0.1700
Data Index: 7575504 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7504. Min Range: -2.7504
Max Act: 2.7024. Min Act: -0.1700
Data Index: 2140085 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7504. Min Range: -2.7504
Max Act: 2.6864. Min Act: -0.1700
Data Index: 7105588 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7504. Min Range: -2.7504
Max Act: 2.6704. Min Act: -0.1700
Data Index: 4247100 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7504. Min Range: -2.7504
Max Act: 2.6383. Min Act: -0.1700
Data Index: 3120412 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7504. Min Range: -2.7504
Max Act: 2.6383. Min Act: -0.1700
Data Index: 5583684 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7504. Min Range: -2.7504
Max Act: 2.6062. Min Act: -0.1700
Data Index: 7480319 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7504. Min Range: -2.7504
Max Act: 2.5901. Min Act: -0.1700
Data Index: 7844421 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7504. Min Range: -2.7504
Max Act: 2.5901. Min Act: -0.1700
Data Index: 6109371 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7504. Min Range: -2.7504
Max Act: 2.5740. Min Act: -0.1700
Data Index: 1830874 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7504. Min Range: -2.7504
Max Act: 2.5740. Min Act: -0.1700
Data Index: 4734962 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7504. Min Range: -2.7504
Max Act: 2.5740. Min Act: -0.1700
Data Index: 5235412 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7504. Min Range: -2.7504
Max Act: 2.5578. Min Act: -0.1700
Data Index: 6894141 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7504. Min Range: -2.7504
Max Act: 2.5578. Min Act: -0.1700
Data Index: 6042250 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7504. Min Range: -2.7504
Max Act: 2.5578. Min Act: -0.1700
Data Index: 5822189 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7504. Min Range: -2.7504
Max Act: 2.5417. Min Act: -0.1700
Data Index: 1729535 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7504. Min Range: -2.7504
Max Act: 2.5417. Min Act: -0.1700
Data Index: 5752267 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7504. Min Range: -2.7504
Max Act: 2.5255. Min Act: -0.1700
Data Index: 6081596 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7504. Min Range: -2.7504
Max Act: 2.5417. Min Act: -0.1700
Data Index: 3865779 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #19