Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5246 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7604. Min Range: -2.7604
Max Act: 2.7604. Min Act: -0.1700
Data Index: 7400330 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7604. Min Range: -2.7604
Max Act: 2.7125. Min Act: -0.1698
Data Index: 7769427 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7604. Min Range: -2.7604
Max Act: 2.6805. Min Act: -0.1700
Data Index: 3563896 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7604. Min Range: -2.7604
Max Act: 2.6805. Min Act: -0.1700
Data Index: 3326505 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7604. Min Range: -2.7604
Max Act: 2.6805. Min Act: -0.1700
Data Index: 489715 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7604. Min Range: -2.7604
Max Act: 2.6805. Min Act: -0.1700
Data Index: 1816878 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7604. Min Range: -2.7604
Max Act: 2.6644. Min Act: -0.1700
Data Index: 5320252 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7604. Min Range: -2.7604
Max Act: 2.6484. Min Act: -0.1700
Data Index: 2293531 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7604. Min Range: -2.7604
Max Act: 2.6484. Min Act: -0.1700
Data Index: 7042807 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7604. Min Range: -2.7604
Max Act: 2.6484. Min Act: -0.1700
Data Index: 2865506 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7604. Min Range: -2.7604
Max Act: 2.6484. Min Act: -0.1700
Data Index: 896204 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7604. Min Range: -2.7604
Max Act: 2.6323. Min Act: -0.1700
Data Index: 4473536 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7604. Min Range: -2.7604
Max Act: 2.6323. Min Act: -0.1700
Data Index: 2483693 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7604. Min Range: -2.7604
Max Act: 2.6163. Min Act: -0.1700
Data Index: 5977155 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7604. Min Range: -2.7604
Max Act: 2.6323. Min Act: -0.1677
Data Index: 4218374 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7604. Min Range: -2.7604
Max Act: 2.6323. Min Act: -0.1700
Data Index: 238358 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7604. Min Range: -2.7604
Max Act: 2.6163. Min Act: -0.1700
Data Index: 3342711 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7604. Min Range: -2.7604
Max Act: 2.6163. Min Act: -0.1700
Data Index: 7089104 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7604. Min Range: -2.7604
Max Act: 2.6002. Min Act: -0.1700
Data Index: 4558173 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7604. Min Range: -2.7604
Max Act: 2.5841. Min Act: -0.1700
Data Index: 3301788 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #19