Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 621 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6680. Min Range: -5.6680
Max Act: 5.6680. Min Act: -0.1700
Data Index: 6577625 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6680. Min Range: -5.6680
Max Act: 5.5743. Min Act: -0.1700
Data Index: 6463135 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6680. Min Range: -5.6680
Max Act: 5.5430. Min Act: -0.1700
Data Index: 2543912 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6680. Min Range: -5.6680
Max Act: 5.5118. Min Act: -0.1700
Data Index: 7692207 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6680. Min Range: -5.6680
Max Act: 5.4805. Min Act: -0.1700
Data Index: 8796976 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6680. Min Range: -5.6680
Max Act: 5.4180. Min Act: -0.1700
Data Index: 3497012 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6680. Min Range: -5.6680
Max Act: 5.4493. Min Act: -0.1700
Data Index: 2972588 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6680. Min Range: -5.6680
Max Act: 5.4493. Min Act: -0.1700
Data Index: 5645700 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6680. Min Range: -5.6680
Max Act: 5.4805. Min Act: -0.1700
Data Index: 5610034 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6680. Min Range: -5.6680
Max Act: 5.4180. Min Act: -0.1700
Data Index: 1611553 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6680. Min Range: -5.6680
Max Act: 5.3868. Min Act: -0.1700
Data Index: 3056416 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6680. Min Range: -5.6680
Max Act: 5.3243. Min Act: -0.1700
Data Index: 3112859 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6680. Min Range: -5.6680
Max Act: 5.3555. Min Act: -0.1700
Data Index: 5597988 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6680. Min Range: -5.6680
Max Act: 5.3868. Min Act: -0.1700
Data Index: 3000 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6680. Min Range: -5.6680
Max Act: 5.3555. Min Act: -0.1700
Data Index: 4897518 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6680. Min Range: -5.6680
Max Act: 5.3555. Min Act: -0.1700
Data Index: 776826 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6680. Min Range: -5.6680
Max Act: 5.3555. Min Act: -0.1700
Data Index: 7501344 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6680. Min Range: -5.6680
Max Act: 5.3555. Min Act: -0.1700
Data Index: 3020573 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6680. Min Range: -5.6680
Max Act: 5.3555. Min Act: -0.1700
Data Index: 1930047 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6680. Min Range: -5.6680
Max Act: 5.3555. Min Act: -0.1700
Data Index: 5427800 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #19