Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 723 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.1006. Min Range: -2.1006
Max Act: 2.1006. Min Act: -0.1700
Data Index: 6440671 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1006. Min Range: -2.1006
Max Act: 2.0670. Min Act: -0.1700
Data Index: 6606260 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1006. Min Range: -2.1006
Max Act: 2.0502. Min Act: -0.1700
Data Index: 1382546 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1006. Min Range: -2.1006
Max Act: 2.0502. Min Act: -0.1700
Data Index: 3195832 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1006. Min Range: -2.1006
Max Act: 2.0334. Min Act: -0.1700
Data Index: 5727362 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1006. Min Range: -2.1006
Max Act: 2.0334. Min Act: -0.1700
Data Index: 3668489 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1006. Min Range: -2.1006
Max Act: 2.0334. Min Act: -0.1700
Data Index: 8580033 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1006. Min Range: -2.1006
Max Act: 2.0165. Min Act: -0.1700
Data Index: 4206152 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1006. Min Range: -2.1006
Max Act: 1.9996. Min Act: -0.1700
Data Index: 7273779 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1006. Min Range: -2.1006
Max Act: 1.9996. Min Act: -0.1700
Data Index: 1612993 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1006. Min Range: -2.1006
Max Act: 1.9827. Min Act: -0.1700
Data Index: 8793723 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1006. Min Range: -2.1006
Max Act: 1.9658. Min Act: -0.1698
Data Index: 4999110 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1006. Min Range: -2.1006
Max Act: 1.9827. Min Act: -0.1700
Data Index: 8255589 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1006. Min Range: -2.1006
Max Act: 1.9827. Min Act: -0.1699
Data Index: 3408434 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1006. Min Range: -2.1006
Max Act: 1.9827. Min Act: -0.1700
Data Index: 315651 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1006. Min Range: -2.1006
Max Act: 1.9658. Min Act: -0.1700
Data Index: 5703533 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1006. Min Range: -2.1006
Max Act: 1.9827. Min Act: -0.1700
Data Index: 415773 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1006. Min Range: -2.1006
Max Act: 1.9827. Min Act: -0.1700
Data Index: 40124 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1006. Min Range: -2.1006
Max Act: 1.9658. Min Act: -0.1700
Data Index: 182766 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1006. Min Range: -2.1006
Max Act: 1.9488. Min Act: -0.1700
Data Index: 7866399 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #19