Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2677 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.0500. Min Range: -1.0500
Max Act: 1.0500. Min Act: -0.1700
Data Index: 4871354 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0500. Min Range: -1.0500
Max Act: 1.0500. Min Act: -0.1700
Data Index: 5681953 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0500. Min Range: -1.0500
Max Act: 1.0065. Min Act: -0.1700
Data Index: 8638720 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0500. Min Range: -1.0500
Max Act: 0.9978. Min Act: -0.1700
Data Index: 805813 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0500. Min Range: -1.0500
Max Act: 1.0152. Min Act: -0.1700
Data Index: 8146019 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0500. Min Range: -1.0500
Max Act: 0.9805. Min Act: -0.1700
Data Index: 6513255 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0500. Min Range: -1.0500
Max Act: 0.9978. Min Act: -0.1700
Data Index: 3557220 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0500. Min Range: -1.0500
Max Act: 0.9892. Min Act: -0.1700
Data Index: 2624051 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0500. Min Range: -1.0500
Max Act: 0.9892. Min Act: -0.1700
Data Index: 3237506 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0500. Min Range: -1.0500
Max Act: 0.9805. Min Act: -0.1700
Data Index: 7464923 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0500. Min Range: -1.0500
Max Act: 0.9892. Min Act: -0.1700
Data Index: 7286936 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0500. Min Range: -1.0500
Max Act: 0.9892. Min Act: -0.1700
Data Index: 6427161 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0500. Min Range: -1.0500
Max Act: 0.9719. Min Act: -0.1700
Data Index: 2683079 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0500. Min Range: -1.0500
Max Act: 0.9805. Min Act: -0.1700
Data Index: 5733835 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0500. Min Range: -1.0500
Max Act: 0.9805. Min Act: -0.1700
Data Index: 2531656 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0500. Min Range: -1.0500
Max Act: 0.9719. Min Act: -0.1700
Data Index: 7166136 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0500. Min Range: -1.0500
Max Act: 0.9805. Min Act: -0.1700
Data Index: 7136509 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0500. Min Range: -1.0500
Max Act: 0.9805. Min Act: -0.1700
Data Index: 6855104 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0500. Min Range: -1.0500
Max Act: 0.9805. Min Act: -0.1700
Data Index: 415593 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0500. Min Range: -1.0500
Max Act: 0.9805. Min Act: -0.1700
Data Index: 1455685 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #19