Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3674 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0701. Min Range: -4.0701
Max Act: 4.0701. Min Act: -0.1700
Data Index: 2005440 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0701. Min Range: -4.0701
Max Act: 4.0388. Min Act: -0.1700
Data Index: 6648742 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0701. Min Range: -4.0701
Max Act: 4.0076. Min Act: -0.1700
Data Index: 958545 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0701. Min Range: -4.0701
Max Act: 4.0076. Min Act: -0.1700
Data Index: 6214869 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0701. Min Range: -4.0701
Max Act: 4.0076. Min Act: -0.1700
Data Index: 150890 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0701. Min Range: -4.0701
Max Act: 3.9450. Min Act: -0.1700
Data Index: 6843610 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0701. Min Range: -4.0701
Max Act: 3.9450. Min Act: -0.1700
Data Index: 249022 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0701. Min Range: -4.0701
Max Act: 3.9450. Min Act: -0.1700
Data Index: 2220279 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0701. Min Range: -4.0701
Max Act: 3.8825. Min Act: -0.1700
Data Index: 924117 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0701. Min Range: -4.0701
Max Act: 3.8512. Min Act: -0.1700
Data Index: 3427250 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0701. Min Range: -4.0701
Max Act: 3.8825. Min Act: -0.1700
Data Index: 1033806 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0701. Min Range: -4.0701
Max Act: 3.8825. Min Act: -0.1700
Data Index: 332061 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0701. Min Range: -4.0701
Max Act: 3.8825. Min Act: -0.1700
Data Index: 7834977 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0701. Min Range: -4.0701
Max Act: 3.8825. Min Act: -0.1700
Data Index: 1543753 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0701. Min Range: -4.0701
Max Act: 3.8512. Min Act: -0.1700
Data Index: 1561405 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0701. Min Range: -4.0701
Max Act: 3.8512. Min Act: -0.1700
Data Index: 7736616 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0701. Min Range: -4.0701
Max Act: 3.7887. Min Act: -0.1700
Data Index: 3706355 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0701. Min Range: -4.0701
Max Act: 3.8200. Min Act: -0.1700
Data Index: 8666844 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0701. Min Range: -4.0701
Max Act: 3.8200. Min Act: -0.1700
Data Index: 7268856 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0701. Min Range: -4.0701
Max Act: 3.7887. Min Act: -0.1700
Data Index: 1033805 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #19