Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3610 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.0996. Min Range: -7.0996
Max Act: 7.0996. Min Act: -0.1700
Data Index: 4403354 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0996. Min Range: -7.0996
Max Act: 6.7871. Min Act: -0.1700
Data Index: 4222684 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0996. Min Range: -7.0996
Max Act: 6.6621. Min Act: -0.1700
Data Index: 3977784 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0996. Min Range: -7.0996
Max Act: 6.6621. Min Act: -0.1700
Data Index: 802631 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0996. Min Range: -7.0996
Max Act: 6.5996. Min Act: -0.1700
Data Index: 6906105 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0996. Min Range: -7.0996
Max Act: 6.5058. Min Act: -0.1700
Data Index: 4749748 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0996. Min Range: -7.0996
Max Act: 6.5371. Min Act: -0.1700
Data Index: 8380695 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0996. Min Range: -7.0996
Max Act: 6.5058. Min Act: -0.1700
Data Index: 4229400 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0996. Min Range: -7.0996
Max Act: 6.5371. Min Act: -0.1700
Data Index: 1809703 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0996. Min Range: -7.0996
Max Act: 6.5058. Min Act: -0.1700
Data Index: 6093595 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0996. Min Range: -7.0996
Max Act: 6.5058. Min Act: -0.1700
Data Index: 4322420 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0996. Min Range: -7.0996
Max Act: 6.4746. Min Act: -0.1700
Data Index: 6480778 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0996. Min Range: -7.0996
Max Act: 6.4746. Min Act: -0.1700
Data Index: 7031733 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0996. Min Range: -7.0996
Max Act: 6.4746. Min Act: -0.1700
Data Index: 7930796 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0996. Min Range: -7.0996
Max Act: 6.4433. Min Act: -0.1700
Data Index: 5090516 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0996. Min Range: -7.0996
Max Act: 6.4433. Min Act: -0.1700
Data Index: 5098498 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0996. Min Range: -7.0996
Max Act: 6.3808. Min Act: -0.1700
Data Index: 669394 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0996. Min Range: -7.0996
Max Act: 6.4121. Min Act: -0.1700
Data Index: 5429743 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0996. Min Range: -7.0996
Max Act: 6.3808. Min Act: -0.1700
Data Index: 932249 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0996. Min Range: -7.0996
Max Act: 6.3808. Min Act: -0.1700
Data Index: 5869570 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19