Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5715 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4337. Min Range: -4.4337
Max Act: 4.4337. Min Act: -0.1700
Data Index: 3498758 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4337. Min Range: -4.4337
Max Act: 4.3399. Min Act: -0.1700
Data Index: 8601512 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4337. Min Range: -4.4337
Max Act: 4.3087. Min Act: -0.1700
Data Index: 7780400 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4337. Min Range: -4.4337
Max Act: 4.2774. Min Act: -0.1700
Data Index: 7638472 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4337. Min Range: -4.4337
Max Act: 4.2774. Min Act: -0.1700
Data Index: 4893926 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4337. Min Range: -4.4337
Max Act: 4.2774. Min Act: -0.1700
Data Index: 8105536 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4337. Min Range: -4.4337
Max Act: 4.2774. Min Act: -0.1700
Data Index: 1714829 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4337. Min Range: -4.4337
Max Act: 4.2149. Min Act: -0.1700
Data Index: 5768874 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4337. Min Range: -4.4337
Max Act: 4.2149. Min Act: -0.1700
Data Index: 5661101 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4337. Min Range: -4.4337
Max Act: 4.2149. Min Act: -0.1700
Data Index: 8707254 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4337. Min Range: -4.4337
Max Act: 4.1837. Min Act: -0.1700
Data Index: 2430342 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4337. Min Range: -4.4337
Max Act: 4.1837. Min Act: -0.1700
Data Index: 8508389 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4337. Min Range: -4.4337
Max Act: 4.1837. Min Act: -0.1700
Data Index: 4632895 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4337. Min Range: -4.4337
Max Act: 4.1837. Min Act: -0.1700
Data Index: 5426732 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4337. Min Range: -4.4337
Max Act: 4.1837. Min Act: -0.1700
Data Index: 1144027 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4337. Min Range: -4.4337
Max Act: 4.1524. Min Act: -0.1700
Data Index: 5770407 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4337. Min Range: -4.4337
Max Act: 4.1524. Min Act: -0.1700
Data Index: 2002602 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4337. Min Range: -4.4337
Max Act: 4.1212. Min Act: -0.1700
Data Index: 1194649 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4337. Min Range: -4.4337
Max Act: 4.1212. Min Act: -0.1700
Data Index: 6040970 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4337. Min Range: -4.4337
Max Act: 4.1212. Min Act: -0.1700
Data Index: 1318904 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #19