Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3477 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9990. Min Range: -4.9990
Max Act: 4.9677. Min Act: -0.1700
Data Index: 5361744 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9990. Min Range: -4.9990
Max Act: 4.9990. Min Act: -0.1700
Data Index: 3830894 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9990. Min Range: -4.9990
Max Act: 4.9677. Min Act: -0.1700
Data Index: 2550009 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9990. Min Range: -4.9990
Max Act: 4.9365. Min Act: -0.1700
Data Index: 5612535 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9990. Min Range: -4.9990
Max Act: 4.9365. Min Act: -0.1700
Data Index: 7733426 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9990. Min Range: -4.9990
Max Act: 4.9052. Min Act: -0.1700
Data Index: 1527180 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9990. Min Range: -4.9990
Max Act: 4.8740. Min Act: -0.1700
Data Index: 515910 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9990. Min Range: -4.9990
Max Act: 4.8740. Min Act: -0.1700
Data Index: 7635326 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9990. Min Range: -4.9990
Max Act: 4.8427. Min Act: -0.1700
Data Index: 7141984 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9990. Min Range: -4.9990
Max Act: 4.8115. Min Act: -0.1700
Data Index: 8431548 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9990. Min Range: -4.9990
Max Act: 4.8115. Min Act: -0.1700
Data Index: 3977983 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9990. Min Range: -4.9990
Max Act: 4.8115. Min Act: -0.1700
Data Index: 2394852 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9990. Min Range: -4.9990
Max Act: 4.8115. Min Act: -0.1700
Data Index: 7036761 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9990. Min Range: -4.9990
Max Act: 4.8427. Min Act: -0.1700
Data Index: 3109178 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9990. Min Range: -4.9990
Max Act: 4.7802. Min Act: -0.1700
Data Index: 4026804 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9990. Min Range: -4.9990
Max Act: 4.8115. Min Act: -0.1700
Data Index: 7018424 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9990. Min Range: -4.9990
Max Act: 4.7802. Min Act: -0.1700
Data Index: 6112206 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9990. Min Range: -4.9990
Max Act: 4.7490. Min Act: -0.1700
Data Index: 1813469 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9990. Min Range: -4.9990
Max Act: 4.7490. Min Act: -0.1700
Data Index: 3788175 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9990. Min Range: -4.9990
Max Act: 4.7802. Min Act: -0.1700
Data Index: 4547465 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #19