Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1828 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4504. Min Range: -6.4504
Max Act: 6.4504. Min Act: -0.1700
Data Index: 592293 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4504. Min Range: -6.4504
Max Act: 6.3567. Min Act: -0.1700
Data Index: 5337218 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4504. Min Range: -6.4504
Max Act: 6.2317. Min Act: -0.1700
Data Index: 1683961 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4504. Min Range: -6.4504
Max Act: 6.1692. Min Act: -0.1700
Data Index: 3024921 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4504. Min Range: -6.4504
Max Act: 6.1067. Min Act: -0.1700
Data Index: 495827 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4504. Min Range: -6.4504
Max Act: 6.1379. Min Act: -0.1700
Data Index: 7350546 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4504. Min Range: -6.4504
Max Act: 6.1067. Min Act: -0.1700
Data Index: 6248237 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4504. Min Range: -6.4504
Max Act: 6.0754. Min Act: -0.1700
Data Index: 6938265 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4504. Min Range: -6.4504
Max Act: 6.0442. Min Act: -0.1700
Data Index: 1656947 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4504. Min Range: -6.4504
Max Act: 6.0442. Min Act: -0.1700
Data Index: 8382149 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4504. Min Range: -6.4504
Max Act: 6.0442. Min Act: -0.1700
Data Index: 4404313 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4504. Min Range: -6.4504
Max Act: 6.0442. Min Act: -0.1700
Data Index: 5761493 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4504. Min Range: -6.4504
Max Act: 6.0754. Min Act: -0.1700
Data Index: 75026 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4504. Min Range: -6.4504
Max Act: 5.9817. Min Act: -0.1700
Data Index: 4698510 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4504. Min Range: -6.4504
Max Act: 6.0129. Min Act: -0.1700
Data Index: 6680845 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4504. Min Range: -6.4504
Max Act: 6.0129. Min Act: -0.1700
Data Index: 1403654 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4504. Min Range: -6.4504
Max Act: 5.9817. Min Act: -0.1700
Data Index: 661487 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4504. Min Range: -6.4504
Max Act: 5.9817. Min Act: -0.1700
Data Index: 6983908 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4504. Min Range: -6.4504
Max Act: 6.0129. Min Act: -0.1700
Data Index: 4812176 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4504. Min Range: -6.4504
Max Act: 5.9192. Min Act: -0.1700
Data Index: 5008596 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19