Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4096 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6092. Min Range: -5.6092
Max Act: 5.6092. Min Act: -0.1700
Data Index: 4301922 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6092. Min Range: -5.6092
Max Act: 5.5155. Min Act: -0.1700
Data Index: 2123711 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6092. Min Range: -5.6092
Max Act: 5.4842. Min Act: -0.1700
Data Index: 2749465 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6092. Min Range: -5.6092
Max Act: 5.4842. Min Act: -0.1700
Data Index: 2529979 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6092. Min Range: -5.6092
Max Act: 5.4530. Min Act: -0.1700
Data Index: 260400 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6092. Min Range: -5.6092
Max Act: 5.4217. Min Act: -0.1700
Data Index: 210784 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6092. Min Range: -5.6092
Max Act: 5.3905. Min Act: -0.1700
Data Index: 186356 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6092. Min Range: -5.6092
Max Act: 5.3905. Min Act: -0.1700
Data Index: 931933 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6092. Min Range: -5.6092
Max Act: 5.3905. Min Act: -0.1700
Data Index: 3856180 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6092. Min Range: -5.6092
Max Act: 5.3592. Min Act: -0.1700
Data Index: 6856846 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6092. Min Range: -5.6092
Max Act: 5.3905. Min Act: -0.1700
Data Index: 5349884 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6092. Min Range: -5.6092
Max Act: 5.3592. Min Act: -0.1700
Data Index: 1036032 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6092. Min Range: -5.6092
Max Act: 5.3592. Min Act: -0.1700
Data Index: 5531026 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6092. Min Range: -5.6092
Max Act: 5.3592. Min Act: -0.1700
Data Index: 5421244 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6092. Min Range: -5.6092
Max Act: 5.3592. Min Act: -0.1700
Data Index: 5518160 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6092. Min Range: -5.6092
Max Act: 5.3280. Min Act: -0.1700
Data Index: 3504954 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6092. Min Range: -5.6092
Max Act: 5.3280. Min Act: -0.1700
Data Index: 5402556 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6092. Min Range: -5.6092
Max Act: 5.3280. Min Act: -0.1700
Data Index: 5402555 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6092. Min Range: -5.6092
Max Act: 5.2967. Min Act: -0.1700
Data Index: 2769916 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6092. Min Range: -5.6092
Max Act: 5.3592. Min Act: -0.1700
Data Index: 4453540 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #19