Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5075 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8641. Min Range: -6.8641
Max Act: 6.8641. Min Act: -0.1700
Data Index: 7797375 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8641. Min Range: -6.8641
Max Act: 6.4891. Min Act: -0.1700
Data Index: 1343768 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8641. Min Range: -6.8641
Max Act: 6.4891. Min Act: -0.1700
Data Index: 2749153 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8641. Min Range: -6.8641
Max Act: 6.3954. Min Act: -0.1700
Data Index: 6156498 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8641. Min Range: -6.8641
Max Act: 6.3641. Min Act: -0.1700
Data Index: 4418877 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8641. Min Range: -6.8641
Max Act: 6.3329. Min Act: -0.1700
Data Index: 1643357 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8641. Min Range: -6.8641
Max Act: 6.3016. Min Act: -0.1700
Data Index: 7653327 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8641. Min Range: -6.8641
Max Act: 6.3016. Min Act: -0.1700
Data Index: 409822 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8641. Min Range: -6.8641
Max Act: 6.2704. Min Act: -0.1700
Data Index: 7322633 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8641. Min Range: -6.8641
Max Act: 6.2391. Min Act: -0.1700
Data Index: 5283205 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8641. Min Range: -6.8641
Max Act: 6.1766. Min Act: -0.1700
Data Index: 427096 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8641. Min Range: -6.8641
Max Act: 6.1454. Min Act: -0.1700
Data Index: 3079900 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8641. Min Range: -6.8641
Max Act: 6.1141. Min Act: -0.1700
Data Index: 8785063 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8641. Min Range: -6.8641
Max Act: 6.0829. Min Act: -0.1700
Data Index: 3905695 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8641. Min Range: -6.8641
Max Act: 6.0516. Min Act: -0.1700
Data Index: 5709855 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8641. Min Range: -6.8641
Max Act: 6.0829. Min Act: -0.1700
Data Index: 282068 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8641. Min Range: -6.8641
Max Act: 6.0516. Min Act: -0.1700
Data Index: 6387873 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8641. Min Range: -6.8641
Max Act: 6.0204. Min Act: -0.1700
Data Index: 585604 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8641. Min Range: -6.8641
Max Act: 6.0204. Min Act: -0.1700
Data Index: 1179391 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8641. Min Range: -6.8641
Max Act: 6.0204. Min Act: -0.1700
Data Index: 2509682 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #19