Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3063 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4767. Min Range: -4.4767
Max Act: 4.4767. Min Act: -0.1700
Data Index: 4807898 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4767. Min Range: -4.4767
Max Act: 4.4455. Min Act: -0.1700
Data Index: 4571898 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4767. Min Range: -4.4767
Max Act: 4.3205. Min Act: -0.1700
Data Index: 2548864 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4767. Min Range: -4.4767
Max Act: 4.2892. Min Act: -0.1700
Data Index: 7242529 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4767. Min Range: -4.4767
Max Act: 4.2580. Min Act: -0.1700
Data Index: 2634986 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4767. Min Range: -4.4767
Max Act: 4.2580. Min Act: -0.1700
Data Index: 313743 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4767. Min Range: -4.4767
Max Act: 4.2267. Min Act: -0.1700
Data Index: 6259714 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4767. Min Range: -4.4767
Max Act: 4.1955. Min Act: -0.1700
Data Index: 1591731 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4767. Min Range: -4.4767
Max Act: 4.2267. Min Act: -0.1700
Data Index: 6940638 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4767. Min Range: -4.4767
Max Act: 4.1329. Min Act: -0.1700
Data Index: 907888 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4767. Min Range: -4.4767
Max Act: 4.1329. Min Act: -0.1700
Data Index: 2756106 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4767. Min Range: -4.4767
Max Act: 4.1329. Min Act: -0.1700
Data Index: 1614441 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4767. Min Range: -4.4767
Max Act: 4.1017. Min Act: -0.1700
Data Index: 7352005 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4767. Min Range: -4.4767
Max Act: 4.1017. Min Act: -0.1700
Data Index: 637773 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4767. Min Range: -4.4767
Max Act: 4.1017. Min Act: -0.1700
Data Index: 6058935 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4767. Min Range: -4.4767
Max Act: 4.0704. Min Act: -0.1700
Data Index: 7602673 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4767. Min Range: -4.4767
Max Act: 4.0704. Min Act: -0.1700
Data Index: 1898215 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4767. Min Range: -4.4767
Max Act: 4.0704. Min Act: -0.1700
Data Index: 7986719 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4767. Min Range: -4.4767
Max Act: 4.0704. Min Act: -0.1700
Data Index: 1964187 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4767. Min Range: -4.4767
Max Act: 4.0704. Min Act: -0.1700
Data Index: 2489398 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #19