Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2107 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3997. Min Range: -6.3997
Max Act: 6.3997. Min Act: -0.1700
Data Index: 1984206 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3997. Min Range: -6.3997
Max Act: 6.3997. Min Act: -0.1700
Data Index: 6697583 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3997. Min Range: -6.3997
Max Act: 6.3685. Min Act: -0.1700
Data Index: 5107972 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3997. Min Range: -6.3997
Max Act: 6.3060. Min Act: -0.1700
Data Index: 83455 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3997. Min Range: -6.3997
Max Act: 6.2747. Min Act: -0.1700
Data Index: 3549779 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3997. Min Range: -6.3997
Max Act: 6.2747. Min Act: -0.1700
Data Index: 2840299 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3997. Min Range: -6.3997
Max Act: 6.2122. Min Act: -0.1700
Data Index: 1187127 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3997. Min Range: -6.3997
Max Act: 6.1810. Min Act: -0.1700
Data Index: 6035251 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3997. Min Range: -6.3997
Max Act: 6.1810. Min Act: -0.1700
Data Index: 1481509 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3997. Min Range: -6.3997
Max Act: 6.1185. Min Act: -0.1700
Data Index: 7115516 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3997. Min Range: -6.3997
Max Act: 6.1185. Min Act: -0.1700
Data Index: 8066154 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3997. Min Range: -6.3997
Max Act: 6.1185. Min Act: -0.1700
Data Index: 5878604 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3997. Min Range: -6.3997
Max Act: 6.1185. Min Act: -0.1700
Data Index: 3884762 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3997. Min Range: -6.3997
Max Act: 6.0872. Min Act: -0.1700
Data Index: 4487624 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3997. Min Range: -6.3997
Max Act: 6.0560. Min Act: -0.1700
Data Index: 827192 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3997. Min Range: -6.3997
Max Act: 6.0560. Min Act: -0.1700
Data Index: 2882064 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3997. Min Range: -6.3997
Max Act: 6.0560. Min Act: -0.1700
Data Index: 5634475 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3997. Min Range: -6.3997
Max Act: 6.0560. Min Act: -0.1700
Data Index: 1550510 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3997. Min Range: -6.3997
Max Act: 6.0247. Min Act: -0.1700
Data Index: 800831 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3997. Min Range: -6.3997
Max Act: 6.0247. Min Act: -0.1700
Data Index: 3304412 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19