Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3823 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9506. Min Range: -7.9506
Max Act: 7.9506. Min Act: -0.1700
Data Index: 5972422 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9506. Min Range: -7.9506
Max Act: 6.9506. Min Act: -0.1700
Data Index: 5476595 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9506. Min Range: -7.9506
Max Act: 6.8881. Min Act: -0.1700
Data Index: 8613123 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9506. Min Range: -7.9506
Max Act: 6.7318. Min Act: -0.1700
Data Index: 5562769 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9506. Min Range: -7.9506
Max Act: 6.7318. Min Act: -0.1700
Data Index: 6947210 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9506. Min Range: -7.9506
Max Act: 6.6381. Min Act: -0.1700
Data Index: 3255156 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9506. Min Range: -7.9506
Max Act: 6.6381. Min Act: -0.1700
Data Index: 7361968 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9506. Min Range: -7.9506
Max Act: 6.6068. Min Act: -0.1700
Data Index: 1494048 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9506. Min Range: -7.9506
Max Act: 6.6068. Min Act: -0.1700
Data Index: 7237261 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9506. Min Range: -7.9506
Max Act: 6.5131. Min Act: -0.1700
Data Index: 7285602 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9506. Min Range: -7.9506
Max Act: 6.4506. Min Act: -0.1700
Data Index: 3867888 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9506. Min Range: -7.9506
Max Act: 6.4818. Min Act: -0.1700
Data Index: 4091761 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9506. Min Range: -7.9506
Max Act: 6.4818. Min Act: -0.1700
Data Index: 4328395 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9506. Min Range: -7.9506
Max Act: 6.5131. Min Act: -0.1700
Data Index: 1360739 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9506. Min Range: -7.9506
Max Act: 6.4193. Min Act: -0.1700
Data Index: 3164803 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9506. Min Range: -7.9506
Max Act: 6.4506. Min Act: -0.1700
Data Index: 1664687 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9506. Min Range: -7.9506
Max Act: 6.4193. Min Act: -0.1700
Data Index: 1897253 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9506. Min Range: -7.9506
Max Act: 6.4193. Min Act: -0.1700
Data Index: 1070720 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9506. Min Range: -7.9506
Max Act: 6.3881. Min Act: -0.1700
Data Index: 2102425 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9506. Min Range: -7.9506
Max Act: 6.4193. Min Act: -0.1700
Data Index: 2151067 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #19