Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1518 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6877. Min Range: -6.6877
Max Act: 6.6877. Min Act: -0.1700
Data Index: 6554202 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6877. Min Range: -6.6877
Max Act: 6.4689. Min Act: -0.1700
Data Index: 4208282 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6877. Min Range: -6.6877
Max Act: 6.4377. Min Act: -0.1700
Data Index: 4079569 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6877. Min Range: -6.6877
Max Act: 6.4064. Min Act: -0.1700
Data Index: 7010970 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6877. Min Range: -6.6877
Max Act: 6.4064. Min Act: -0.1700
Data Index: 199708 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6877. Min Range: -6.6877
Max Act: 6.3752. Min Act: -0.1700
Data Index: 4537548 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6877. Min Range: -6.6877
Max Act: 6.3752. Min Act: -0.1700
Data Index: 694162 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6877. Min Range: -6.6877
Max Act: 6.3752. Min Act: -0.1700
Data Index: 3770337 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6877. Min Range: -6.6877
Max Act: 6.3752. Min Act: -0.1700
Data Index: 404442 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6877. Min Range: -6.6877
Max Act: 6.3127. Min Act: -0.1700
Data Index: 7385092 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6877. Min Range: -6.6877
Max Act: 6.2814. Min Act: -0.1700
Data Index: 2111572 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6877. Min Range: -6.6877
Max Act: 6.2502. Min Act: -0.1700
Data Index: 4547023 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6877. Min Range: -6.6877
Max Act: 6.2502. Min Act: -0.1700
Data Index: 2994336 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6877. Min Range: -6.6877
Max Act: 6.2189. Min Act: -0.1700
Data Index: 6861366 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6877. Min Range: -6.6877
Max Act: 6.2502. Min Act: -0.1700
Data Index: 6525353 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6877. Min Range: -6.6877
Max Act: 6.1564. Min Act: -0.1700
Data Index: 5951530 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6877. Min Range: -6.6877
Max Act: 6.1564. Min Act: -0.1700
Data Index: 1559130 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6877. Min Range: -6.6877
Max Act: 6.1564. Min Act: -0.1700
Data Index: 5468588 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6877. Min Range: -6.6877
Max Act: 6.0939. Min Act: -0.1700
Data Index: 3063000 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6877. Min Range: -6.6877
Max Act: 6.1252. Min Act: -0.1700
Data Index: 1551553 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #19