Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3437 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9727. Min Range: -5.9727
Max Act: 5.9727. Min Act: -0.1700
Data Index: 4858904 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9727. Min Range: -5.9727
Max Act: 5.7227. Min Act: -0.1700
Data Index: 1036899 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9727. Min Range: -5.9727
Max Act: 5.4727. Min Act: -0.1700
Data Index: 3223065 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9727. Min Range: -5.9727
Max Act: 5.5040. Min Act: -0.1700
Data Index: 5862994 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9727. Min Range: -5.9727
Max Act: 5.4415. Min Act: -0.1700
Data Index: 8249177 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9727. Min Range: -5.9727
Max Act: 5.3790. Min Act: -0.1700
Data Index: 7411593 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9727. Min Range: -5.9727
Max Act: 5.3790. Min Act: -0.1700
Data Index: 1003283 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9727. Min Range: -5.9727
Max Act: 5.3477. Min Act: -0.1700
Data Index: 88780 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9727. Min Range: -5.9727
Max Act: 5.3477. Min Act: -0.1700
Data Index: 1231232 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9727. Min Range: -5.9727
Max Act: 5.3165. Min Act: -0.1700
Data Index: 8170733 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9727. Min Range: -5.9727
Max Act: 5.2852. Min Act: -0.1700
Data Index: 7777157 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9727. Min Range: -5.9727
Max Act: 5.2227. Min Act: -0.1700
Data Index: 5873739 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9727. Min Range: -5.9727
Max Act: 5.1602. Min Act: -0.1700
Data Index: 6777727 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9727. Min Range: -5.9727
Max Act: 5.1602. Min Act: -0.1700
Data Index: 39895 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9727. Min Range: -5.9727
Max Act: 5.1290. Min Act: -0.1700
Data Index: 2204325 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9727. Min Range: -5.9727
Max Act: 5.1290. Min Act: -0.1700
Data Index: 4605804 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9727. Min Range: -5.9727
Max Act: 5.0977. Min Act: -0.1700
Data Index: 6694269 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9727. Min Range: -5.9727
Max Act: 5.0665. Min Act: -0.1700
Data Index: 5594688 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9727. Min Range: -5.9727
Max Act: 5.0352. Min Act: -0.1700
Data Index: 5691470 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9727. Min Range: -5.9727
Max Act: 5.0352. Min Act: -0.1700
Data Index: 4114348 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19