Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3106 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0878. Min Range: -6.0878
Max Act: 6.0878. Min Act: -0.1700
Data Index: 8821133 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0878. Min Range: -6.0878
Max Act: 6.0253. Min Act: -0.1700
Data Index: 5428912 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0878. Min Range: -6.0878
Max Act: 5.9003. Min Act: -0.1700
Data Index: 5594112 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0878. Min Range: -6.0878
Max Act: 5.8378. Min Act: -0.1700
Data Index: 7841184 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0878. Min Range: -6.0878
Max Act: 5.7753. Min Act: -0.1700
Data Index: 3247993 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0878. Min Range: -6.0878
Max Act: 5.7441. Min Act: -0.1700
Data Index: 4911433 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0878. Min Range: -6.0878
Max Act: 5.7753. Min Act: -0.1700
Data Index: 2737597 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0878. Min Range: -6.0878
Max Act: 5.7128. Min Act: -0.1700
Data Index: 2387345 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0878. Min Range: -6.0878
Max Act: 5.7128. Min Act: -0.1700
Data Index: 4061345 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0878. Min Range: -6.0878
Max Act: 5.7128. Min Act: -0.1700
Data Index: 4565403 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0878. Min Range: -6.0878
Max Act: 5.6816. Min Act: -0.1700
Data Index: 4142186 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0878. Min Range: -6.0878
Max Act: 5.6816. Min Act: -0.1700
Data Index: 4580721 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0878. Min Range: -6.0878
Max Act: 5.6816. Min Act: -0.1700
Data Index: 206512 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0878. Min Range: -6.0878
Max Act: 5.6191. Min Act: -0.1700
Data Index: 7689679 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0878. Min Range: -6.0878
Max Act: 5.5878. Min Act: -0.1700
Data Index: 4265435 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0878. Min Range: -6.0878
Max Act: 5.5566. Min Act: -0.1700
Data Index: 8638574 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0878. Min Range: -6.0878
Max Act: 5.5566. Min Act: -0.1700
Data Index: 4388336 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0878. Min Range: -6.0878
Max Act: 5.5566. Min Act: -0.1700
Data Index: 1413532 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0878. Min Range: -6.0878
Max Act: 5.5253. Min Act: -0.1700
Data Index: 4291067 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0878. Min Range: -6.0878
Max Act: 5.5253. Min Act: -0.1700
Data Index: 6080786 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #19