Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4500 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7371. Min Range: -6.7371
Max Act: 6.7371. Min Act: -0.1700
Data Index: 509253 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7371. Min Range: -6.7371
Max Act: 6.6121. Min Act: -0.1700
Data Index: 6880373 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7371. Min Range: -6.7371
Max Act: 6.4871. Min Act: -0.1700
Data Index: 858509 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7371. Min Range: -6.7371
Max Act: 6.4559. Min Act: -0.1700
Data Index: 509250 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7371. Min Range: -6.7371
Max Act: 6.4559. Min Act: -0.1700
Data Index: 3938267 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7371. Min Range: -6.7371
Max Act: 6.4559. Min Act: -0.1700
Data Index: 3284189 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7371. Min Range: -6.7371
Max Act: 6.4246. Min Act: -0.1700
Data Index: 7583430 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7371. Min Range: -6.7371
Max Act: 6.4559. Min Act: -0.1700
Data Index: 1203572 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7371. Min Range: -6.7371
Max Act: 6.3934. Min Act: -0.1700
Data Index: 115296 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7371. Min Range: -6.7371
Max Act: 6.3934. Min Act: -0.1700
Data Index: 3690982 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7371. Min Range: -6.7371
Max Act: 6.3934. Min Act: -0.1700
Data Index: 5598957 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7371. Min Range: -6.7371
Max Act: 6.3934. Min Act: -0.1700
Data Index: 6053483 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7371. Min Range: -6.7371
Max Act: 6.3934. Min Act: -0.1700
Data Index: 1706108 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7371. Min Range: -6.7371
Max Act: 6.3621. Min Act: -0.1700
Data Index: 1681878 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7371. Min Range: -6.7371
Max Act: 6.3621. Min Act: -0.1700
Data Index: 6903608 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7371. Min Range: -6.7371
Max Act: 6.3621. Min Act: -0.1700
Data Index: 6159036 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7371. Min Range: -6.7371
Max Act: 6.3309. Min Act: -0.1700
Data Index: 815358 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7371. Min Range: -6.7371
Max Act: 6.3309. Min Act: -0.1700
Data Index: 3730450 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7371. Min Range: -6.7371
Max Act: 6.3309. Min Act: -0.1700
Data Index: 7583029 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7371. Min Range: -6.7371
Max Act: 6.3309. Min Act: -0.1700
Data Index: 4844733 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #19