Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2912 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2712. Min Range: -6.2712
Max Act: 6.2712. Min Act: -0.1700
Data Index: 1157815 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2712. Min Range: -6.2712
Max Act: 6.2712. Min Act: -0.1700
Data Index: 3586009 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2712. Min Range: -6.2712
Max Act: 6.2712. Min Act: -0.1700
Data Index: 3138444 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2712. Min Range: -6.2712
Max Act: 6.2400. Min Act: -0.1700
Data Index: 7015021 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2712. Min Range: -6.2712
Max Act: 6.2087. Min Act: -0.1700
Data Index: 681774 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2712. Min Range: -6.2712
Max Act: 6.1775. Min Act: -0.1700
Data Index: 1907114 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2712. Min Range: -6.2712
Max Act: 6.1462. Min Act: -0.1700
Data Index: 2763315 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2712. Min Range: -6.2712
Max Act: 6.1462. Min Act: -0.1700
Data Index: 764658 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2712. Min Range: -6.2712
Max Act: 6.1150. Min Act: -0.1700
Data Index: 6714212 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2712. Min Range: -6.2712
Max Act: 6.1150. Min Act: -0.1700
Data Index: 4540784 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2712. Min Range: -6.2712
Max Act: 6.1150. Min Act: -0.1700
Data Index: 611136 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2712. Min Range: -6.2712
Max Act: 6.0837. Min Act: -0.1700
Data Index: 5037370 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2712. Min Range: -6.2712
Max Act: 6.0837. Min Act: -0.1700
Data Index: 2916888 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2712. Min Range: -6.2712
Max Act: 6.0837. Min Act: -0.1700
Data Index: 8137406 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2712. Min Range: -6.2712
Max Act: 6.0837. Min Act: -0.1700
Data Index: 7372263 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2712. Min Range: -6.2712
Max Act: 6.0837. Min Act: -0.1700
Data Index: 652012 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2712. Min Range: -6.2712
Max Act: 6.0525. Min Act: -0.1700
Data Index: 1292527 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2712. Min Range: -6.2712
Max Act: 6.0525. Min Act: -0.1700
Data Index: 8102285 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2712. Min Range: -6.2712
Max Act: 6.0212. Min Act: -0.1700
Data Index: 6020211 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2712. Min Range: -6.2712
Max Act: 6.0212. Min Act: -0.1700
Data Index: 6099996 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #19