Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3512 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0068. Min Range: -5.0068
Max Act: 5.0068. Min Act: -0.1700
Data Index: 879179 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0068. Min Range: -5.0068
Max Act: 4.9131. Min Act: -0.1700
Data Index: 660278 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0068. Min Range: -5.0068
Max Act: 4.8818. Min Act: -0.1700
Data Index: 6544697 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0068. Min Range: -5.0068
Max Act: 4.8193. Min Act: -0.1700
Data Index: 3165036 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0068. Min Range: -5.0068
Max Act: 4.7881. Min Act: -0.1700
Data Index: 8638367 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0068. Min Range: -5.0068
Max Act: 4.7256. Min Act: -0.1700
Data Index: 7543040 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0068. Min Range: -5.0068
Max Act: 4.6318. Min Act: -0.1700
Data Index: 5696480 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0068. Min Range: -5.0068
Max Act: 4.6318. Min Act: -0.1700
Data Index: 5176657 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0068. Min Range: -5.0068
Max Act: 4.6006. Min Act: -0.1700
Data Index: 6114211 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0068. Min Range: -5.0068
Max Act: 4.5693. Min Act: -0.1700
Data Index: 1099818 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0068. Min Range: -5.0068
Max Act: 4.5693. Min Act: -0.1700
Data Index: 6325096 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0068. Min Range: -5.0068
Max Act: 4.5693. Min Act: -0.1700
Data Index: 3381834 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0068. Min Range: -5.0068
Max Act: 4.6318. Min Act: -0.1700
Data Index: 4326185 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0068. Min Range: -5.0068
Max Act: 4.6006. Min Act: -0.1700
Data Index: 6497828 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0068. Min Range: -5.0068
Max Act: 4.5693. Min Act: -0.1700
Data Index: 7295928 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0068. Min Range: -5.0068
Max Act: 4.5693. Min Act: -0.1700
Data Index: 8014377 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0068. Min Range: -5.0068
Max Act: 4.5068. Min Act: -0.1700
Data Index: 6890855 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0068. Min Range: -5.0068
Max Act: 4.5693. Min Act: -0.1700
Data Index: 218311 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0068. Min Range: -5.0068
Max Act: 4.5380. Min Act: -0.1700
Data Index: 3755587 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0068. Min Range: -5.0068
Max Act: 4.5380. Min Act: -0.1700
Data Index: 2905696 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #19