Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3039 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5065. Min Range: -4.5065
Max Act: 4.5065. Min Act: -0.1700
Data Index: 1938415 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5065. Min Range: -4.5065
Max Act: 4.3815. Min Act: -0.1700
Data Index: 8098805 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5065. Min Range: -4.5065
Max Act: 4.3503. Min Act: -0.1700
Data Index: 6583804 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5065. Min Range: -4.5065
Max Act: 4.3503. Min Act: -0.1700
Data Index: 2076313 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5065. Min Range: -4.5065
Max Act: 4.3190. Min Act: -0.1700
Data Index: 3670609 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5065. Min Range: -4.5065
Max Act: 4.1940. Min Act: -0.1700
Data Index: 6764208 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5065. Min Range: -4.5065
Max Act: 4.1940. Min Act: -0.1700
Data Index: 7329896 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5065. Min Range: -4.5065
Max Act: 4.1940. Min Act: -0.1700
Data Index: 5858509 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5065. Min Range: -4.5065
Max Act: 4.1940. Min Act: -0.1700
Data Index: 8402313 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5065. Min Range: -4.5065
Max Act: 4.1627. Min Act: -0.1700
Data Index: 1067201 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5065. Min Range: -4.5065
Max Act: 4.1627. Min Act: -0.1700
Data Index: 4970377 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5065. Min Range: -4.5065
Max Act: 4.1627. Min Act: -0.1700
Data Index: 820542 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5065. Min Range: -4.5065
Max Act: 4.1627. Min Act: -0.1700
Data Index: 3575435 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5065. Min Range: -4.5065
Max Act: 4.1627. Min Act: -0.1700
Data Index: 5421532 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5065. Min Range: -4.5065
Max Act: 4.1315. Min Act: -0.1700
Data Index: 2908403 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5065. Min Range: -4.5065
Max Act: 4.1315. Min Act: -0.1700
Data Index: 2009122 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5065. Min Range: -4.5065
Max Act: 4.1315. Min Act: -0.1700
Data Index: 4953272 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5065. Min Range: -4.5065
Max Act: 4.1315. Min Act: -0.1700
Data Index: 5250045 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5065. Min Range: -4.5065
Max Act: 4.1002. Min Act: -0.1700
Data Index: 8023167 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5065. Min Range: -4.5065
Max Act: 4.1002. Min Act: -0.1700
Data Index: 4650067 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #19