Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1683 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1940. Min Range: -4.1940
Max Act: 4.1940. Min Act: -0.1700
Data Index: 4960559 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1940. Min Range: -4.1940
Max Act: 4.1940. Min Act: -0.1700
Data Index: 914921 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1940. Min Range: -4.1940
Max Act: 4.1628. Min Act: -0.1700
Data Index: 2784019 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1940. Min Range: -4.1940
Max Act: 4.1628. Min Act: -0.1700
Data Index: 921789 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1940. Min Range: -4.1940
Max Act: 4.1315. Min Act: -0.1700
Data Index: 97965 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1940. Min Range: -4.1940
Max Act: 4.1628. Min Act: -0.1700
Data Index: 546941 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1940. Min Range: -4.1940
Max Act: 4.1003. Min Act: -0.1700
Data Index: 5427625 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1940. Min Range: -4.1940
Max Act: 4.0690. Min Act: -0.1700
Data Index: 8502327 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1940. Min Range: -4.1940
Max Act: 4.0690. Min Act: -0.1700
Data Index: 1730894 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1940. Min Range: -4.1940
Max Act: 4.0690. Min Act: -0.1700
Data Index: 4680774 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1940. Min Range: -4.1940
Max Act: 4.0690. Min Act: -0.1700
Data Index: 321043 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1940. Min Range: -4.1940
Max Act: 4.0690. Min Act: -0.1700
Data Index: 1276849 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1940. Min Range: -4.1940
Max Act: 4.0690. Min Act: -0.1700
Data Index: 4616148 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1940. Min Range: -4.1940
Max Act: 4.0690. Min Act: -0.1700
Data Index: 3780607 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1940. Min Range: -4.1940
Max Act: 4.0377. Min Act: -0.1700
Data Index: 8033084 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1940. Min Range: -4.1940
Max Act: 4.0377. Min Act: -0.1700
Data Index: 1769231 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1940. Min Range: -4.1940
Max Act: 4.0065. Min Act: -0.1700
Data Index: 4455460 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1940. Min Range: -4.1940
Max Act: 4.0377. Min Act: -0.1700
Data Index: 466357 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1940. Min Range: -4.1940
Max Act: 4.0065. Min Act: -0.1700
Data Index: 8214813 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1940. Min Range: -4.1940
Max Act: 3.9440. Min Act: -0.1700
Data Index: 6371036 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #19