Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3190 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0027. Min Range: -7.0027
Max Act: 7.0027. Min Act: -0.1700
Data Index: 7265401 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0027. Min Range: -7.0027
Max Act: 6.9714. Min Act: -0.1700
Data Index: 7917034 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0027. Min Range: -7.0027
Max Act: 6.9402. Min Act: -0.1700
Data Index: 8275743 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0027. Min Range: -7.0027
Max Act: 6.8464. Min Act: -0.1700
Data Index: 937859 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0027. Min Range: -7.0027
Max Act: 6.7839. Min Act: -0.1700
Data Index: 5803380 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0027. Min Range: -7.0027
Max Act: 6.6902. Min Act: -0.1700
Data Index: 4748847 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0027. Min Range: -7.0027
Max Act: 6.6277. Min Act: -0.1700
Data Index: 6431056 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0027. Min Range: -7.0027
Max Act: 6.6277. Min Act: -0.1700
Data Index: 3636750 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0027. Min Range: -7.0027
Max Act: 6.6277. Min Act: -0.1700
Data Index: 1735639 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0027. Min Range: -7.0027
Max Act: 6.5964. Min Act: -0.1700
Data Index: 4397932 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0027. Min Range: -7.0027
Max Act: 6.5964. Min Act: -0.1700
Data Index: 8260634 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0027. Min Range: -7.0027
Max Act: 6.5652. Min Act: -0.1700
Data Index: 4516864 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0027. Min Range: -7.0027
Max Act: 6.5652. Min Act: -0.1700
Data Index: 1310881 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0027. Min Range: -7.0027
Max Act: 6.5652. Min Act: -0.1700
Data Index: 3989443 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0027. Min Range: -7.0027
Max Act: 6.5652. Min Act: -0.1700
Data Index: 3391513 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0027. Min Range: -7.0027
Max Act: 6.5339. Min Act: -0.1700
Data Index: 3140378 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0027. Min Range: -7.0027
Max Act: 6.5339. Min Act: -0.1700
Data Index: 5839990 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0027. Min Range: -7.0027
Max Act: 6.5027. Min Act: -0.1700
Data Index: 6335045 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0027. Min Range: -7.0027
Max Act: 6.4714. Min Act: -0.1700
Data Index: 7078579 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0027. Min Range: -7.0027
Max Act: 6.4714. Min Act: -0.1700
Data Index: 7503293 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #19