Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2997 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6767. Min Range: -5.6767
Max Act: 5.6767. Min Act: -0.1700
Data Index: 4083763 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6767. Min Range: -5.6767
Max Act: 5.6455. Min Act: -0.1700
Data Index: 5831219 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6767. Min Range: -5.6767
Max Act: 5.6142. Min Act: -0.1700
Data Index: 3859615 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6767. Min Range: -5.6767
Max Act: 5.5830. Min Act: -0.1700
Data Index: 5444853 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6767. Min Range: -5.6767
Max Act: 5.5517. Min Act: -0.1700
Data Index: 4141240 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6767. Min Range: -5.6767
Max Act: 5.5517. Min Act: -0.1700
Data Index: 2993138 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6767. Min Range: -5.6767
Max Act: 5.5205. Min Act: -0.1700
Data Index: 104805 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6767. Min Range: -5.6767
Max Act: 5.5517. Min Act: -0.1700
Data Index: 5241407 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6767. Min Range: -5.6767
Max Act: 5.5205. Min Act: -0.1700
Data Index: 3207482 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6767. Min Range: -5.6767
Max Act: 5.4892. Min Act: -0.1700
Data Index: 7618974 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6767. Min Range: -5.6767
Max Act: 5.4892. Min Act: -0.1700
Data Index: 95339 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6767. Min Range: -5.6767
Max Act: 5.4892. Min Act: -0.1700
Data Index: 414848 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6767. Min Range: -5.6767
Max Act: 5.4892. Min Act: -0.1700
Data Index: 954052 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6767. Min Range: -5.6767
Max Act: 5.4580. Min Act: -0.1700
Data Index: 2224131 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6767. Min Range: -5.6767
Max Act: 5.4892. Min Act: -0.1700
Data Index: 5866858 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6767. Min Range: -5.6767
Max Act: 5.4580. Min Act: -0.1700
Data Index: 7564550 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6767. Min Range: -5.6767
Max Act: 5.4580. Min Act: -0.1700
Data Index: 3009196 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6767. Min Range: -5.6767
Max Act: 5.4580. Min Act: -0.1700
Data Index: 6870821 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6767. Min Range: -5.6767
Max Act: 5.4267. Min Act: -0.1700
Data Index: 649257 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6767. Min Range: -5.6767
Max Act: 5.4267. Min Act: -0.1700
Data Index: 6744598 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #19