Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4775 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.4914. Min Range: -11.4914
Max Act: 11.4914. Min Act: -0.1700
Data Index: 6382032 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.4914. Min Range: -11.4914
Max Act: 11.3039. Min Act: -0.1700
Data Index: 175062 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.4914. Min Range: -11.4914
Max Act: 11.3039. Min Act: -0.1700
Data Index: 54945 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.4914. Min Range: -11.4914
Max Act: 11.2414. Min Act: -0.1700
Data Index: 3932068 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.4914. Min Range: -11.4914
Max Act: 11.3039. Min Act: -0.1700
Data Index: 2441992 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.4914. Min Range: -11.4914
Max Act: 11.1789. Min Act: -0.1700
Data Index: 878162 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.4914. Min Range: -11.4914
Max Act: 11.1789. Min Act: -0.1700
Data Index: 2440919 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.4914. Min Range: -11.4914
Max Act: 11.1164. Min Act: -0.1700
Data Index: 2877916 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.4914. Min Range: -11.4914
Max Act: 11.1164. Min Act: -0.1699
Data Index: 6579085 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.4914. Min Range: -11.4914
Max Act: 11.1164. Min Act: -0.1700
Data Index: 2572871 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.4914. Min Range: -11.4914
Max Act: 11.1164. Min Act: -0.1700
Data Index: 1584853 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.4914. Min Range: -11.4914
Max Act: 11.1164. Min Act: -0.1700
Data Index: 1296679 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.4914. Min Range: -11.4914
Max Act: 11.0539. Min Act: -0.1700
Data Index: 2724827 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.4914. Min Range: -11.4914
Max Act: 11.0539. Min Act: -0.1700
Data Index: 7464432 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.4914. Min Range: -11.4914
Max Act: 10.9914. Min Act: -0.1700
Data Index: 1325050 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.4914. Min Range: -11.4914
Max Act: 10.9289. Min Act: -0.1700
Data Index: 3043539 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.4914. Min Range: -11.4914
Max Act: 10.9289. Min Act: -0.1700
Data Index: 7382979 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.4914. Min Range: -11.4914
Max Act: 10.9289. Min Act: -0.1700
Data Index: 7126213 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.4914. Min Range: -11.4914
Max Act: 10.9289. Min Act: -0.1700
Data Index: 3501754 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.4914. Min Range: -11.4914
Max Act: 11.0539. Min Act: -0.1700
Data Index: 1852896 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #19