Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1718 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8516. Min Range: -7.8516
Max Act: 7.8516. Min Act: -0.1700
Data Index: 2887750 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8516. Min Range: -7.8516
Max Act: 7.7891. Min Act: -0.1700
Data Index: 4016645 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8516. Min Range: -7.8516
Max Act: 7.6641. Min Act: -0.1700
Data Index: 7919736 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8516. Min Range: -7.8516
Max Act: 7.5704. Min Act: -0.1700
Data Index: 3683036 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8516. Min Range: -7.8516
Max Act: 7.4141. Min Act: -0.1700
Data Index: 4924975 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8516. Min Range: -7.8516
Max Act: 7.3829. Min Act: -0.1700
Data Index: 3990706 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8516. Min Range: -7.8516
Max Act: 7.3516. Min Act: -0.1700
Data Index: 3003226 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8516. Min Range: -7.8516
Max Act: 7.2579. Min Act: -0.1700
Data Index: 3806560 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8516. Min Range: -7.8516
Max Act: 7.1954. Min Act: -0.1700
Data Index: 7630355 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8516. Min Range: -7.8516
Max Act: 7.1641. Min Act: -0.1700
Data Index: 6651020 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8516. Min Range: -7.8516
Max Act: 7.1954. Min Act: -0.1700
Data Index: 5492261 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8516. Min Range: -7.8516
Max Act: 7.1641. Min Act: -0.1700
Data Index: 3683035 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8516. Min Range: -7.8516
Max Act: 7.1329. Min Act: -0.1700
Data Index: 4368804 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8516. Min Range: -7.8516
Max Act: 7.1329. Min Act: -0.1700
Data Index: 1080207 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8516. Min Range: -7.8516
Max Act: 7.1641. Min Act: -0.1700
Data Index: 6474887 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8516. Min Range: -7.8516
Max Act: 7.1329. Min Act: -0.1700
Data Index: 5982513 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8516. Min Range: -7.8516
Max Act: 7.1641. Min Act: -0.1700
Data Index: 5099260 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8516. Min Range: -7.8516
Max Act: 7.1641. Min Act: -0.1700
Data Index: 6159128 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8516. Min Range: -7.8516
Max Act: 7.1329. Min Act: -0.1700
Data Index: 673102 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8516. Min Range: -7.8516
Max Act: 7.1329. Min Act: -0.1700
Data Index: 5331144 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #19