Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2186 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1998. Min Range: -5.1998
Max Act: 5.1998. Min Act: -0.1700
Data Index: 7306570 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1998. Min Range: -5.1998
Max Act: 5.1685. Min Act: -0.1700
Data Index: 1016147 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1998. Min Range: -5.1998
Max Act: 5.1373. Min Act: -0.1700
Data Index: 979950 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1998. Min Range: -5.1998
Max Act: 5.1685. Min Act: -0.1700
Data Index: 3348030 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1998. Min Range: -5.1998
Max Act: 5.1060. Min Act: -0.1700
Data Index: 1933062 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1998. Min Range: -5.1998
Max Act: 5.1060. Min Act: -0.1700
Data Index: 4400505 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1998. Min Range: -5.1998
Max Act: 5.0748. Min Act: -0.1700
Data Index: 5635291 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1998. Min Range: -5.1998
Max Act: 5.0748. Min Act: -0.1700
Data Index: 4972313 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1998. Min Range: -5.1998
Max Act: 5.0748. Min Act: -0.1700
Data Index: 7272500 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1998. Min Range: -5.1998
Max Act: 5.0435. Min Act: -0.1700
Data Index: 1316298 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1998. Min Range: -5.1998
Max Act: 5.0435. Min Act: -0.1700
Data Index: 7021949 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1998. Min Range: -5.1998
Max Act: 5.0435. Min Act: -0.1700
Data Index: 3473555 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1998. Min Range: -5.1998
Max Act: 5.0435. Min Act: -0.1700
Data Index: 851875 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1998. Min Range: -5.1998
Max Act: 5.0435. Min Act: -0.1700
Data Index: 2326773 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1998. Min Range: -5.1998
Max Act: 5.0123. Min Act: -0.1700
Data Index: 2743675 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1998. Min Range: -5.1998
Max Act: 5.0123. Min Act: -0.1700
Data Index: 4462591 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1998. Min Range: -5.1998
Max Act: 5.0123. Min Act: -0.1700
Data Index: 2504194 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1998. Min Range: -5.1998
Max Act: 5.0123. Min Act: -0.1700
Data Index: 6927822 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1998. Min Range: -5.1998
Max Act: 5.0123. Min Act: -0.1700
Data Index: 6554067 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1998. Min Range: -5.1998
Max Act: 4.9810. Min Act: -0.1700
Data Index: 1282678 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #19