Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5918 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2127. Min Range: -5.2127
Max Act: 5.2127. Min Act: -0.1700
Data Index: 8731799 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2127. Min Range: -5.2127
Max Act: 5.1814. Min Act: -0.1700
Data Index: 6142428 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2127. Min Range: -5.2127
Max Act: 5.1189. Min Act: -0.1700
Data Index: 6477752 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2127. Min Range: -5.2127
Max Act: 5.1189. Min Act: -0.1700
Data Index: 6507215 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2127. Min Range: -5.2127
Max Act: 5.0877. Min Act: -0.1700
Data Index: 7362343 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2127. Min Range: -5.2127
Max Act: 5.0564. Min Act: -0.1700
Data Index: 3958644 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2127. Min Range: -5.2127
Max Act: 4.9939. Min Act: -0.1700
Data Index: 4089585 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2127. Min Range: -5.2127
Max Act: 4.9939. Min Act: -0.1700
Data Index: 1373680 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2127. Min Range: -5.2127
Max Act: 4.9627. Min Act: -0.1700
Data Index: 7251200 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2127. Min Range: -5.2127
Max Act: 4.9627. Min Act: -0.1700
Data Index: 2288120 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2127. Min Range: -5.2127
Max Act: 4.9627. Min Act: -0.1700
Data Index: 7611737 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2127. Min Range: -5.2127
Max Act: 4.9314. Min Act: -0.1700
Data Index: 3005647 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2127. Min Range: -5.2127
Max Act: 4.9002. Min Act: -0.1700
Data Index: 1782079 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2127. Min Range: -5.2127
Max Act: 4.9002. Min Act: -0.1700
Data Index: 1599065 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2127. Min Range: -5.2127
Max Act: 4.9002. Min Act: -0.1700
Data Index: 3606794 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2127. Min Range: -5.2127
Max Act: 4.9002. Min Act: -0.1700
Data Index: 6681891 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2127. Min Range: -5.2127
Max Act: 4.8689. Min Act: -0.1700
Data Index: 2969626 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2127. Min Range: -5.2127
Max Act: 4.8689. Min Act: -0.1700
Data Index: 2698748 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2127. Min Range: -5.2127
Max Act: 4.8377. Min Act: -0.1700
Data Index: 2518701 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2127. Min Range: -5.2127
Max Act: 4.7752. Min Act: -0.1700
Data Index: 3747324 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #19