Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1417 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7813. Min Range: -5.7813
Max Act: 5.7813. Min Act: -0.1700
Data Index: 6837115 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7813. Min Range: -5.7813
Max Act: 5.7188. Min Act: -0.1700
Data Index: 4603919 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7813. Min Range: -5.7813
Max Act: 5.5938. Min Act: -0.1700
Data Index: 5144248 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7813. Min Range: -5.7813
Max Act: 5.5625. Min Act: -0.1700
Data Index: 3670882 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7813. Min Range: -5.7813
Max Act: 5.5313. Min Act: -0.1700
Data Index: 1794536 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7813. Min Range: -5.7813
Max Act: 5.5625. Min Act: -0.1700
Data Index: 7984549 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7813. Min Range: -5.7813
Max Act: 5.5625. Min Act: -0.1700
Data Index: 781918 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7813. Min Range: -5.7813
Max Act: 5.5313. Min Act: -0.1700
Data Index: 1551138 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7813. Min Range: -5.7813
Max Act: 5.5000. Min Act: -0.1700
Data Index: 2231767 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7813. Min Range: -5.7813
Max Act: 5.4375. Min Act: -0.1700
Data Index: 4926324 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7813. Min Range: -5.7813
Max Act: 5.4688. Min Act: -0.1700
Data Index: 5089435 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7813. Min Range: -5.7813
Max Act: 5.4688. Min Act: -0.1700
Data Index: 4767026 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7813. Min Range: -5.7813
Max Act: 5.4688. Min Act: -0.1700
Data Index: 6106447 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7813. Min Range: -5.7813
Max Act: 5.4063. Min Act: -0.1700
Data Index: 7620495 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7813. Min Range: -5.7813
Max Act: 5.3750. Min Act: -0.1700
Data Index: 5947450 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7813. Min Range: -5.7813
Max Act: 5.3750. Min Act: -0.1700
Data Index: 5156365 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7813. Min Range: -5.7813
Max Act: 5.3750. Min Act: -0.1700
Data Index: 2406552 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7813. Min Range: -5.7813
Max Act: 5.3750. Min Act: -0.1700
Data Index: 6263299 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7813. Min Range: -5.7813
Max Act: 5.3750. Min Act: -0.1700
Data Index: 2840166 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7813. Min Range: -5.7813
Max Act: 5.3438. Min Act: -0.1700
Data Index: 7868571 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #19