Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4754 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6430. Min Range: -4.6430
Max Act: 4.6430. Min Act: -0.1700
Data Index: 4575494 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6430. Min Range: -4.6430
Max Act: 4.6118. Min Act: -0.1700
Data Index: 4809913 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6430. Min Range: -4.6430
Max Act: 4.6118. Min Act: -0.1700
Data Index: 8301754 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6430. Min Range: -4.6430
Max Act: 4.6118. Min Act: -0.1700
Data Index: 6461250 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6430. Min Range: -4.6430
Max Act: 4.5805. Min Act: -0.1700
Data Index: 4263939 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6430. Min Range: -4.6430
Max Act: 4.5805. Min Act: -0.1700
Data Index: 3413440 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6430. Min Range: -4.6430
Max Act: 4.5805. Min Act: -0.1700
Data Index: 3077853 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6430. Min Range: -4.6430
Max Act: 4.5805. Min Act: -0.1700
Data Index: 7673910 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6430. Min Range: -4.6430
Max Act: 4.6118. Min Act: -0.1700
Data Index: 7648808 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6430. Min Range: -4.6430
Max Act: 4.5805. Min Act: -0.1700
Data Index: 6941414 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6430. Min Range: -4.6430
Max Act: 4.5493. Min Act: -0.1700
Data Index: 2702825 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6430. Min Range: -4.6430
Max Act: 4.5805. Min Act: -0.1700
Data Index: 2069136 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6430. Min Range: -4.6430
Max Act: 4.5180. Min Act: -0.1700
Data Index: 7044926 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6430. Min Range: -4.6430
Max Act: 4.5493. Min Act: -0.1700
Data Index: 7247464 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6430. Min Range: -4.6430
Max Act: 4.5493. Min Act: -0.1700
Data Index: 6546467 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6430. Min Range: -4.6430
Max Act: 4.5180. Min Act: -0.1700
Data Index: 6465201 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6430. Min Range: -4.6430
Max Act: 4.5493. Min Act: -0.1700
Data Index: 3311619 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6430. Min Range: -4.6430
Max Act: 4.5493. Min Act: -0.1700
Data Index: 5289064 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6430. Min Range: -4.6430
Max Act: 4.5493. Min Act: -0.1700
Data Index: 8739305 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6430. Min Range: -4.6430
Max Act: 4.5180. Min Act: -0.1700
Data Index: 2291201 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #19