Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2715 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9215. Min Range: -6.9215
Max Act: 6.9215. Min Act: -0.1700
Data Index: 4145805 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9215. Min Range: -6.9215
Max Act: 6.7653. Min Act: -0.1700
Data Index: 6604705 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9215. Min Range: -6.9215
Max Act: 6.7028. Min Act: -0.1700
Data Index: 8012685 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9215. Min Range: -6.9215
Max Act: 6.7028. Min Act: -0.1700
Data Index: 7463154 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9215. Min Range: -6.9215
Max Act: 6.6090. Min Act: -0.1700
Data Index: 2398380 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9215. Min Range: -6.9215
Max Act: 6.5153. Min Act: -0.1700
Data Index: 7463156 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9215. Min Range: -6.9215
Max Act: 6.5153. Min Act: -0.1700
Data Index: 8332149 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9215. Min Range: -6.9215
Max Act: 6.3903. Min Act: -0.1700
Data Index: 7345210 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9215. Min Range: -6.9215
Max Act: 6.4215. Min Act: -0.1700
Data Index: 6895742 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9215. Min Range: -6.9215
Max Act: 6.3903. Min Act: -0.1700
Data Index: 5688344 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9215. Min Range: -6.9215
Max Act: 6.3903. Min Act: -0.1700
Data Index: 736851 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9215. Min Range: -6.9215
Max Act: 6.3590. Min Act: -0.1700
Data Index: 1765294 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9215. Min Range: -6.9215
Max Act: 6.3278. Min Act: -0.1700
Data Index: 5929360 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9215. Min Range: -6.9215
Max Act: 6.3278. Min Act: -0.1700
Data Index: 8079899 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9215. Min Range: -6.9215
Max Act: 6.3278. Min Act: -0.1700
Data Index: 7345208 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9215. Min Range: -6.9215
Max Act: 6.2965. Min Act: -0.1700
Data Index: 2389978 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9215. Min Range: -6.9215
Max Act: 6.2653. Min Act: -0.1700
Data Index: 2353003 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9215. Min Range: -6.9215
Max Act: 6.2653. Min Act: -0.1700
Data Index: 4860932 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9215. Min Range: -6.9215
Max Act: 6.2653. Min Act: -0.1700
Data Index: 1348722 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9215. Min Range: -6.9215
Max Act: 6.2340. Min Act: -0.1700
Data Index: 5448077 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #19