Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2838 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9056. Min Range: -5.9056
Max Act: 5.9056. Min Act: -0.1700
Data Index: 3255974 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9056. Min Range: -5.9056
Max Act: 5.8743. Min Act: -0.1700
Data Index: 2821006 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9056. Min Range: -5.9056
Max Act: 5.7806. Min Act: -0.1700
Data Index: 8132305 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9056. Min Range: -5.9056
Max Act: 5.7493. Min Act: -0.1700
Data Index: 8150409 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9056. Min Range: -5.9056
Max Act: 5.6868. Min Act: -0.1700
Data Index: 5909301 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9056. Min Range: -5.9056
Max Act: 5.6868. Min Act: -0.1700
Data Index: 4021578 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9056. Min Range: -5.9056
Max Act: 5.6556. Min Act: -0.1700
Data Index: 1747903 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9056. Min Range: -5.9056
Max Act: 5.6556. Min Act: -0.1700
Data Index: 1489276 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9056. Min Range: -5.9056
Max Act: 5.6556. Min Act: -0.1700
Data Index: 8061937 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9056. Min Range: -5.9056
Max Act: 5.6556. Min Act: -0.1700
Data Index: 615631 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9056. Min Range: -5.9056
Max Act: 5.6556. Min Act: -0.1700
Data Index: 569026 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9056. Min Range: -5.9056
Max Act: 5.6556. Min Act: -0.1700
Data Index: 7960489 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9056. Min Range: -5.9056
Max Act: 5.6556. Min Act: -0.1700
Data Index: 7941960 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9056. Min Range: -5.9056
Max Act: 5.6556. Min Act: -0.1700
Data Index: 6532119 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9056. Min Range: -5.9056
Max Act: 5.6243. Min Act: -0.1700
Data Index: 6003890 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9056. Min Range: -5.9056
Max Act: 5.6243. Min Act: -0.1700
Data Index: 7260397 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9056. Min Range: -5.9056
Max Act: 5.6243. Min Act: -0.1700
Data Index: 497326 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9056. Min Range: -5.9056
Max Act: 5.5931. Min Act: -0.1698
Data Index: 4005409 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9056. Min Range: -5.9056
Max Act: 5.6243. Min Act: -0.1700
Data Index: 4726385 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9056. Min Range: -5.9056
Max Act: 5.6243. Min Act: -0.1700
Data Index: 7949764 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #19