Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3314 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0001. Min Range: -7.0001
Max Act: 7.0001. Min Act: -0.1700
Data Index: 4163187 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0001. Min Range: -7.0001
Max Act: 6.6563. Min Act: -0.1700
Data Index: 2579671 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0001. Min Range: -7.0001
Max Act: 6.6563. Min Act: -0.1700
Data Index: 5173471 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0001. Min Range: -7.0001
Max Act: 6.6251. Min Act: -0.1700
Data Index: 6312985 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0001. Min Range: -7.0001
Max Act: 6.5938. Min Act: -0.1700
Data Index: 3728996 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0001. Min Range: -7.0001
Max Act: 6.4063. Min Act: -0.1700
Data Index: 5228047 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0001. Min Range: -7.0001
Max Act: 6.3751. Min Act: -0.1700
Data Index: 7083073 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0001. Min Range: -7.0001
Max Act: 6.3751. Min Act: -0.1700
Data Index: 2569958 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0001. Min Range: -7.0001
Max Act: 6.3438. Min Act: -0.1700
Data Index: 2313187 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0001. Min Range: -7.0001
Max Act: 6.2813. Min Act: -0.1700
Data Index: 5124884 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0001. Min Range: -7.0001
Max Act: 6.2813. Min Act: -0.1700
Data Index: 49979 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0001. Min Range: -7.0001
Max Act: 6.3126. Min Act: -0.1700
Data Index: 5062118 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0001. Min Range: -7.0001
Max Act: 6.2501. Min Act: -0.1700
Data Index: 3995220 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0001. Min Range: -7.0001
Max Act: 6.2188. Min Act: -0.1700
Data Index: 8714439 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0001. Min Range: -7.0001
Max Act: 6.2188. Min Act: -0.1700
Data Index: 6220387 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0001. Min Range: -7.0001
Max Act: 6.2501. Min Act: -0.1700
Data Index: 1591117 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0001. Min Range: -7.0001
Max Act: 6.2188. Min Act: -0.1700
Data Index: 6902521 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0001. Min Range: -7.0001
Max Act: 6.1876. Min Act: -0.1700
Data Index: 920103 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0001. Min Range: -7.0001
Max Act: 6.1876. Min Act: -0.1700
Data Index: 5377460 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0001. Min Range: -7.0001
Max Act: 6.1563. Min Act: -0.1700
Data Index: 8110714 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #19