Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2786 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4620. Min Range: -5.4620
Max Act: 5.4620. Min Act: -0.1700
Data Index: 617638 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4620. Min Range: -5.4620
Max Act: 5.2433. Min Act: -0.1700
Data Index: 1966376 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4620. Min Range: -5.4620
Max Act: 5.1495. Min Act: -0.1700
Data Index: 3739318 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4620. Min Range: -5.4620
Max Act: 5.1183. Min Act: -0.1700
Data Index: 6049357 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4620. Min Range: -5.4620
Max Act: 5.1183. Min Act: -0.1700
Data Index: 2839345 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4620. Min Range: -5.4620
Max Act: 5.1183. Min Act: -0.1700
Data Index: 3561276 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4620. Min Range: -5.4620
Max Act: 5.1183. Min Act: -0.1700
Data Index: 8660569 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4620. Min Range: -5.4620
Max Act: 5.0870. Min Act: -0.1700
Data Index: 7105254 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4620. Min Range: -5.4620
Max Act: 5.0870. Min Act: -0.1700
Data Index: 1821034 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4620. Min Range: -5.4620
Max Act: 5.0870. Min Act: -0.1700
Data Index: 5177868 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4620. Min Range: -5.4620
Max Act: 5.0870. Min Act: -0.1700
Data Index: 4617081 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4620. Min Range: -5.4620
Max Act: 5.0558. Min Act: -0.1700
Data Index: 3811478 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4620. Min Range: -5.4620
Max Act: 4.9620. Min Act: -0.1700
Data Index: 8042858 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4620. Min Range: -5.4620
Max Act: 5.0245. Min Act: -0.1700
Data Index: 7324330 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4620. Min Range: -5.4620
Max Act: 4.9933. Min Act: -0.1700
Data Index: 2147118 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4620. Min Range: -5.4620
Max Act: 4.9933. Min Act: -0.1700
Data Index: 4626832 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4620. Min Range: -5.4620
Max Act: 4.9620. Min Act: -0.1700
Data Index: 6250305 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4620. Min Range: -5.4620
Max Act: 4.9933. Min Act: -0.1700
Data Index: 844083 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4620. Min Range: -5.4620
Max Act: 4.9620. Min Act: -0.1700
Data Index: 8690380 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4620. Min Range: -5.4620
Max Act: 4.9620. Min Act: -0.1700
Data Index: 5172595 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #19