Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5364 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1295. Min Range: -5.1295
Max Act: 5.1295. Min Act: -0.1700
Data Index: 4979031 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1295. Min Range: -5.1295
Max Act: 5.0982. Min Act: -0.1700
Data Index: 1835714 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1295. Min Range: -5.1295
Max Act: 5.0357. Min Act: -0.1700
Data Index: 4676066 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1295. Min Range: -5.1295
Max Act: 5.0357. Min Act: -0.1700
Data Index: 3463525 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1295. Min Range: -5.1295
Max Act: 5.0357. Min Act: -0.1700
Data Index: 1804181 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1295. Min Range: -5.1295
Max Act: 5.0045. Min Act: -0.1700
Data Index: 1153815 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.9732. Min Act: -0.1700
Data Index: 2634578 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1295. Min Range: -5.1295
Max Act: 5.0045. Min Act: -0.1700
Data Index: 3864194 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1295. Min Range: -5.1295
Max Act: 5.0045. Min Act: -0.1700
Data Index: 1436402 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1295. Min Range: -5.1295
Max Act: 5.0045. Min Act: -0.1700
Data Index: 740891 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1295. Min Range: -5.1295
Max Act: 5.0045. Min Act: -0.1700
Data Index: 729255 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.9732. Min Act: -0.1700
Data Index: 51937 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.9732. Min Act: -0.1700
Data Index: 4118488 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.9732. Min Act: -0.1700
Data Index: 3755161 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.9732. Min Act: -0.1700
Data Index: 684964 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.9732. Min Act: -0.1700
Data Index: 1220814 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.9732. Min Act: -0.1700
Data Index: 2670036 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.9732. Min Act: -0.1700
Data Index: 2696876 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.9732. Min Act: -0.1700
Data Index: 2527707 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1295. Min Range: -5.1295
Max Act: 5.0045. Min Act: -0.1700
Data Index: 3662843 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #19