Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1995 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2188. Min Range: -4.2188
Max Act: 4.2188. Min Act: -0.1700
Data Index: 4012844 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2188. Min Range: -4.2188
Max Act: 4.1876. Min Act: -0.1700
Data Index: 6405115 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2188. Min Range: -4.2188
Max Act: 3.9688. Min Act: -0.1700
Data Index: 6936273 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2188. Min Range: -4.2188
Max Act: 3.9688. Min Act: -0.1700
Data Index: 6989288 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2188. Min Range: -4.2188
Max Act: 3.9375. Min Act: -0.1700
Data Index: 4519409 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2188. Min Range: -4.2188
Max Act: 3.9375. Min Act: -0.1700
Data Index: 5590720 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2188. Min Range: -4.2188
Max Act: 3.9375. Min Act: -0.1700
Data Index: 1075606 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2188. Min Range: -4.2188
Max Act: 3.9375. Min Act: -0.1700
Data Index: 4247714 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2188. Min Range: -4.2188
Max Act: 3.8437. Min Act: -0.1700
Data Index: 5870370 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2188. Min Range: -4.2188
Max Act: 3.8750. Min Act: -0.1700
Data Index: 3515479 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2188. Min Range: -4.2188
Max Act: 3.8750. Min Act: -0.1700
Data Index: 5503753 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2188. Min Range: -4.2188
Max Act: 3.8437. Min Act: -0.1700
Data Index: 6313912 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2188. Min Range: -4.2188
Max Act: 3.8437. Min Act: -0.1700
Data Index: 886492 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2188. Min Range: -4.2188
Max Act: 3.8437. Min Act: -0.1700
Data Index: 937766 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2188. Min Range: -4.2188
Max Act: 3.8437. Min Act: -0.1700
Data Index: 7819955 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2188. Min Range: -4.2188
Max Act: 3.8124. Min Act: -0.1700
Data Index: 1035007 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2188. Min Range: -4.2188
Max Act: 3.7812. Min Act: -0.1700
Data Index: 7436702 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2188. Min Range: -4.2188
Max Act: 3.8124. Min Act: -0.1700
Data Index: 8480054 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2188. Min Range: -4.2188
Max Act: 3.8124. Min Act: -0.1700
Data Index: 2413806 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2188. Min Range: -4.2188
Max Act: 3.7812. Min Act: -0.1700
Data Index: 74159 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #19