Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 901 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1103. Min Range: -5.1103
Max Act: 5.1103. Min Act: -0.1700
Data Index: 3589801 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1103. Min Range: -5.1103
Max Act: 5.0791. Min Act: -0.1700
Data Index: 1364198 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1103. Min Range: -5.1103
Max Act: 5.0478. Min Act: -0.1700
Data Index: 5809745 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1103. Min Range: -5.1103
Max Act: 5.0478. Min Act: -0.1700
Data Index: 2921386 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1103. Min Range: -5.1103
Max Act: 5.0478. Min Act: -0.1700
Data Index: 2987358 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1103. Min Range: -5.1103
Max Act: 5.0478. Min Act: -0.1700
Data Index: 3850941 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1103. Min Range: -5.1103
Max Act: 5.0166. Min Act: -0.1700
Data Index: 1274510 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1103. Min Range: -5.1103
Max Act: 4.9853. Min Act: -0.1700
Data Index: 5214936 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1103. Min Range: -5.1103
Max Act: 5.0166. Min Act: -0.1700
Data Index: 2477260 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1103. Min Range: -5.1103
Max Act: 5.0166. Min Act: -0.1700
Data Index: 1638409 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1103. Min Range: -5.1103
Max Act: 5.0166. Min Act: -0.1700
Data Index: 7919414 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1103. Min Range: -5.1103
Max Act: 5.0166. Min Act: -0.1700
Data Index: 7689801 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1103. Min Range: -5.1103
Max Act: 5.0166. Min Act: -0.1700
Data Index: 7149831 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1103. Min Range: -5.1103
Max Act: 5.0166. Min Act: -0.1700
Data Index: 5995727 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1103. Min Range: -5.1103
Max Act: 4.9853. Min Act: -0.1700
Data Index: 1523794 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1103. Min Range: -5.1103
Max Act: 4.9853. Min Act: -0.1700
Data Index: 1669388 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1103. Min Range: -5.1103
Max Act: 4.9853. Min Act: -0.1700
Data Index: 483013 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1103. Min Range: -5.1103
Max Act: 4.9853. Min Act: -0.1700
Data Index: 3505451 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1103. Min Range: -5.1103
Max Act: 4.9853. Min Act: -0.1700
Data Index: 2432124 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1103. Min Range: -5.1103
Max Act: 4.9541. Min Act: -0.1700
Data Index: 148473 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19