Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2522 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5589. Min Range: -6.5589
Max Act: 6.5589. Min Act: -0.1700
Data Index: 5885551 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5589. Min Range: -6.5589
Max Act: 6.3402. Min Act: -0.1700
Data Index: 6400840 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5589. Min Range: -6.5589
Max Act: 6.2777. Min Act: -0.1700
Data Index: 7146565 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5589. Min Range: -6.5589
Max Act: 6.2464. Min Act: -0.1700
Data Index: 5774462 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5589. Min Range: -6.5589
Max Act: 6.2464. Min Act: -0.1700
Data Index: 6777083 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5589. Min Range: -6.5589
Max Act: 6.2152. Min Act: -0.1700
Data Index: 5140005 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5589. Min Range: -6.5589
Max Act: 6.2152. Min Act: -0.1700
Data Index: 4252357 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5589. Min Range: -6.5589
Max Act: 6.1527. Min Act: -0.1700
Data Index: 4199760 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5589. Min Range: -6.5589
Max Act: 6.1527. Min Act: -0.1700
Data Index: 8322794 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5589. Min Range: -6.5589
Max Act: 6.0902. Min Act: -0.1700
Data Index: 6282541 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5589. Min Range: -6.5589
Max Act: 6.0902. Min Act: -0.1700
Data Index: 4199762 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5589. Min Range: -6.5589
Max Act: 6.0902. Min Act: -0.1700
Data Index: 1030581 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5589. Min Range: -6.5589
Max Act: 6.1214. Min Act: -0.1700
Data Index: 6198264 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5589. Min Range: -6.5589
Max Act: 6.0902. Min Act: -0.1700
Data Index: 4870259 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5589. Min Range: -6.5589
Max Act: 6.0902. Min Act: -0.1700
Data Index: 3366120 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5589. Min Range: -6.5589
Max Act: 6.0589. Min Act: -0.1700
Data Index: 3092437 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5589. Min Range: -6.5589
Max Act: 6.0589. Min Act: -0.1700
Data Index: 194885 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5589. Min Range: -6.5589
Max Act: 6.0902. Min Act: -0.1700
Data Index: 1162774 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5589. Min Range: -6.5589
Max Act: 6.0589. Min Act: -0.1700
Data Index: 2501922 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5589. Min Range: -6.5589
Max Act: 6.0589. Min Act: -0.1700
Data Index: 6756988 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19