Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1977 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.1861. Min Range: -2.1861
Max Act: 2.1861. Min Act: -0.1700
Data Index: 4408455 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1861. Min Range: -2.1861
Max Act: 2.0187. Min Act: -0.1700
Data Index: 2774134 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1861. Min Range: -2.1861
Max Act: 2.0018. Min Act: -0.1700
Data Index: 6835544 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1861. Min Range: -2.1861
Max Act: 1.9680. Min Act: -0.1700
Data Index: 7527262 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1861. Min Range: -2.1861
Max Act: 1.9680. Min Act: -0.1700
Data Index: 7556585 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1861. Min Range: -2.1861
Max Act: 1.9510. Min Act: -0.1700
Data Index: 5202160 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1861. Min Range: -2.1861
Max Act: 1.9340. Min Act: -0.1700
Data Index: 6515318 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1861. Min Range: -2.1861
Max Act: 1.9340. Min Act: -0.1700
Data Index: 4048468 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1861. Min Range: -2.1861
Max Act: 1.9170. Min Act: -0.1700
Data Index: 5153852 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1861. Min Range: -2.1861
Max Act: 1.9340. Min Act: -0.1700
Data Index: 4893558 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1861. Min Range: -2.1861
Max Act: 1.9170. Min Act: -0.1700
Data Index: 612782 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1861. Min Range: -2.1861
Max Act: 1.8829. Min Act: -0.1700
Data Index: 4523409 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1861. Min Range: -2.1861
Max Act: 1.9000. Min Act: -0.1700
Data Index: 1543141 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1861. Min Range: -2.1861
Max Act: 1.9000. Min Act: -0.1700
Data Index: 2180908 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1861. Min Range: -2.1861
Max Act: 1.9000. Min Act: -0.1700
Data Index: 4877736 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1861. Min Range: -2.1861
Max Act: 1.8829. Min Act: -0.1700
Data Index: 1698832 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1861. Min Range: -2.1861
Max Act: 1.8829. Min Act: -0.1700
Data Index: 8140990 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1861. Min Range: -2.1861
Max Act: 1.8829. Min Act: -0.1700
Data Index: 3157352 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1861. Min Range: -2.1861
Max Act: 1.8658. Min Act: -0.1700
Data Index: 1453297 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1861. Min Range: -2.1861
Max Act: 1.8658. Min Act: -0.1700
Data Index: 4362618 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #19