Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3212 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9932. Min Range: -5.9932
Max Act: 5.9932. Min Act: -0.1700
Data Index: 2953704 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9932. Min Range: -5.9932
Max Act: 5.9620. Min Act: -0.1700
Data Index: 6949409 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9932. Min Range: -5.9932
Max Act: 5.9307. Min Act: -0.1700
Data Index: 5329512 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9932. Min Range: -5.9932
Max Act: 5.8682. Min Act: -0.1700
Data Index: 8749334 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9932. Min Range: -5.9932
Max Act: 5.8682. Min Act: -0.1700
Data Index: 4812204 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9932. Min Range: -5.9932
Max Act: 5.8370. Min Act: -0.1700
Data Index: 3756258 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9932. Min Range: -5.9932
Max Act: 5.8057. Min Act: -0.1700
Data Index: 8020813 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9932. Min Range: -5.9932
Max Act: 5.8057. Min Act: -0.1700
Data Index: 1812504 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9932. Min Range: -5.9932
Max Act: 5.8057. Min Act: -0.1700
Data Index: 7947305 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9932. Min Range: -5.9932
Max Act: 5.7745. Min Act: -0.1700
Data Index: 139541 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9932. Min Range: -5.9932
Max Act: 5.7745. Min Act: -0.1700
Data Index: 1110440 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9932. Min Range: -5.9932
Max Act: 5.7745. Min Act: -0.1700
Data Index: 4193312 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9932. Min Range: -5.9932
Max Act: 5.7745. Min Act: -0.1700
Data Index: 1992697 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9932. Min Range: -5.9932
Max Act: 5.7432. Min Act: -0.1700
Data Index: 7015128 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9932. Min Range: -5.9932
Max Act: 5.7432. Min Act: -0.1700
Data Index: 2062329 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9932. Min Range: -5.9932
Max Act: 5.7432. Min Act: -0.1700
Data Index: 3087394 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9932. Min Range: -5.9932
Max Act: 5.7432. Min Act: -0.1700
Data Index: 5883250 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9932. Min Range: -5.9932
Max Act: 5.7432. Min Act: -0.1700
Data Index: 3438067 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9932. Min Range: -5.9932
Max Act: 5.6807. Min Act: -0.1700
Data Index: 4886483 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9932. Min Range: -5.9932
Max Act: 5.7120. Min Act: -0.1700
Data Index: 5501708 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #19