Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3442 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3080. Min Range: -5.3080
Max Act: 5.3080. Min Act: -0.1700
Data Index: 5831516 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3080. Min Range: -5.3080
Max Act: 5.2767. Min Act: -0.1700
Data Index: 1342918 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3080. Min Range: -5.3080
Max Act: 5.2142. Min Act: -0.1700
Data Index: 7190684 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3080. Min Range: -5.3080
Max Act: 5.2142. Min Act: -0.1700
Data Index: 6461498 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3080. Min Range: -5.3080
Max Act: 5.1517. Min Act: -0.1700
Data Index: 2384092 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3080. Min Range: -5.3080
Max Act: 5.1517. Min Act: -0.1700
Data Index: 3561613 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3080. Min Range: -5.3080
Max Act: 5.0892. Min Act: -0.1700
Data Index: 7690441 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3080. Min Range: -5.3080
Max Act: 4.9955. Min Act: -0.1700
Data Index: 8823400 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3080. Min Range: -5.3080
Max Act: 4.9955. Min Act: -0.1700
Data Index: 7555889 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3080. Min Range: -5.3080
Max Act: 4.9642. Min Act: -0.1700
Data Index: 4108002 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3080. Min Range: -5.3080
Max Act: 4.9955. Min Act: -0.1700
Data Index: 4623248 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3080. Min Range: -5.3080
Max Act: 4.9642. Min Act: -0.1700
Data Index: 2522758 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3080. Min Range: -5.3080
Max Act: 4.9642. Min Act: -0.1700
Data Index: 7119249 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3080. Min Range: -5.3080
Max Act: 4.9330. Min Act: -0.1700
Data Index: 6957104 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3080. Min Range: -5.3080
Max Act: 4.9330. Min Act: -0.1700
Data Index: 1025696 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3080. Min Range: -5.3080
Max Act: 4.8705. Min Act: -0.1700
Data Index: 3987786 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3080. Min Range: -5.3080
Max Act: 4.8705. Min Act: -0.1700
Data Index: 7647891 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3080. Min Range: -5.3080
Max Act: 4.8705. Min Act: -0.1700
Data Index: 6627048 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3080. Min Range: -5.3080
Max Act: 4.8392. Min Act: -0.1700
Data Index: 3555756 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3080. Min Range: -5.3080
Max Act: 4.8705. Min Act: -0.1700
Data Index: 1025697 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #19