Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1798 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1880. Min Range: -6.1880
Max Act: 6.1880. Min Act: -0.1700
Data Index: 4747234 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1880. Min Range: -6.1880
Max Act: 6.1880. Min Act: -0.1700
Data Index: 444784 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1880. Min Range: -6.1880
Max Act: 6.0630. Min Act: -0.1700
Data Index: 1556605 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1880. Min Range: -6.1880
Max Act: 5.9380. Min Act: -0.1700
Data Index: 7872225 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1880. Min Range: -6.1880
Max Act: 5.9068. Min Act: -0.1700
Data Index: 1592174 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1880. Min Range: -6.1880
Max Act: 5.8443. Min Act: -0.1700
Data Index: 2176303 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1880. Min Range: -6.1880
Max Act: 5.8755. Min Act: -0.1700
Data Index: 5648525 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1880. Min Range: -6.1880
Max Act: 5.8755. Min Act: -0.1700
Data Index: 5539736 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1880. Min Range: -6.1880
Max Act: 5.8755. Min Act: -0.1700
Data Index: 394813 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1880. Min Range: -6.1880
Max Act: 5.8443. Min Act: -0.1700
Data Index: 1103026 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1880. Min Range: -6.1880
Max Act: 5.8130. Min Act: -0.1700
Data Index: 1614329 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1880. Min Range: -6.1880
Max Act: 5.8443. Min Act: -0.1700
Data Index: 3773788 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1880. Min Range: -6.1880
Max Act: 5.8443. Min Act: -0.1700
Data Index: 7320219 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1880. Min Range: -6.1880
Max Act: 5.8443. Min Act: -0.1700
Data Index: 4305669 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1880. Min Range: -6.1880
Max Act: 5.8443. Min Act: -0.1700
Data Index: 341789 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1880. Min Range: -6.1880
Max Act: 5.8130. Min Act: -0.1700
Data Index: 4574245 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1880. Min Range: -6.1880
Max Act: 5.7818. Min Act: -0.1700
Data Index: 5078660 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1880. Min Range: -6.1880
Max Act: 5.8130. Min Act: -0.1700
Data Index: 3507905 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1880. Min Range: -6.1880
Max Act: 5.8130. Min Act: -0.1700
Data Index: 3711727 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1880. Min Range: -6.1880
Max Act: 5.8130. Min Act: -0.1700
Data Index: 1740401 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #19