Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6389 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0743. Min Range: -7.0743
Max Act: 7.0743. Min Act: -0.1700
Data Index: 1925300 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0743. Min Range: -7.0743
Max Act: 7.0430. Min Act: -0.1700
Data Index: 8198571 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0743. Min Range: -7.0743
Max Act: 6.9805. Min Act: -0.1700
Data Index: 1332682 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0743. Min Range: -7.0743
Max Act: 6.9180. Min Act: -0.1700
Data Index: 5490366 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0743. Min Range: -7.0743
Max Act: 6.8868. Min Act: -0.1700
Data Index: 1098711 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0743. Min Range: -7.0743
Max Act: 6.8243. Min Act: -0.1700
Data Index: 6040104 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0743. Min Range: -7.0743
Max Act: 6.7618. Min Act: -0.1700
Data Index: 3031673 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0743. Min Range: -7.0743
Max Act: 6.7618. Min Act: -0.1700
Data Index: 1039082 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0743. Min Range: -7.0743
Max Act: 6.7618. Min Act: -0.1700
Data Index: 8766640 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0743. Min Range: -7.0743
Max Act: 6.7305. Min Act: -0.1700
Data Index: 6252473 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0743. Min Range: -7.0743
Max Act: 6.7305. Min Act: -0.1700
Data Index: 2703663 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0743. Min Range: -7.0743
Max Act: 6.7305. Min Act: -0.1700
Data Index: 4344231 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0743. Min Range: -7.0743
Max Act: 6.6680. Min Act: -0.1700
Data Index: 2231397 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0743. Min Range: -7.0743
Max Act: 6.6680. Min Act: -0.1700
Data Index: 8473472 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0743. Min Range: -7.0743
Max Act: 6.6680. Min Act: -0.1700
Data Index: 7992412 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0743. Min Range: -7.0743
Max Act: 6.6368. Min Act: -0.1700
Data Index: 9283 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0743. Min Range: -7.0743
Max Act: 6.6055. Min Act: -0.1700
Data Index: 5607399 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0743. Min Range: -7.0743
Max Act: 6.5743. Min Act: -0.1700
Data Index: 1925302 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0743. Min Range: -7.0743
Max Act: 6.5430. Min Act: -0.1700
Data Index: 2812924 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0743. Min Range: -7.0743
Max Act: 6.5743. Min Act: -0.1700
Data Index: 998173 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #19