Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 56 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5066. Min Range: -6.5066
Max Act: 6.5066. Min Act: -0.1700
Data Index: 3398801 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5066. Min Range: -6.5066
Max Act: 6.3503. Min Act: -0.1700
Data Index: 1740881 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5066. Min Range: -6.5066
Max Act: 6.1941. Min Act: -0.1700
Data Index: 6875220 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5066. Min Range: -6.5066
Max Act: 6.1628. Min Act: -0.1700
Data Index: 6383756 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5066. Min Range: -6.5066
Max Act: 6.1628. Min Act: -0.1700
Data Index: 8492715 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5066. Min Range: -6.5066
Max Act: 6.1003. Min Act: -0.1700
Data Index: 4407194 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5066. Min Range: -6.5066
Max Act: 6.1628. Min Act: -0.1700
Data Index: 7906309 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5066. Min Range: -6.5066
Max Act: 6.1316. Min Act: -0.1700
Data Index: 774577 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5066. Min Range: -6.5066
Max Act: 6.1003. Min Act: -0.1700
Data Index: 3299538 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5066. Min Range: -6.5066
Max Act: 6.1316. Min Act: -0.1700
Data Index: 107891 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5066. Min Range: -6.5066
Max Act: 6.0691. Min Act: -0.1700
Data Index: 4457621 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5066. Min Range: -6.5066
Max Act: 6.0691. Min Act: -0.1700
Data Index: 5245050 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5066. Min Range: -6.5066
Max Act: 6.0691. Min Act: -0.1700
Data Index: 2544610 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5066. Min Range: -6.5066
Max Act: 6.0066. Min Act: -0.1700
Data Index: 7188928 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5066. Min Range: -6.5066
Max Act: 6.0378. Min Act: -0.1700
Data Index: 8615572 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5066. Min Range: -6.5066
Max Act: 6.0066. Min Act: -0.1700
Data Index: 7399861 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5066. Min Range: -6.5066
Max Act: 6.0378. Min Act: -0.1700
Data Index: 7615750 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5066. Min Range: -6.5066
Max Act: 6.0066. Min Act: -0.1700
Data Index: 3499439 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5066. Min Range: -6.5066
Max Act: 6.0066. Min Act: -0.1700
Data Index: 1784324 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5066. Min Range: -6.5066
Max Act: 6.0066. Min Act: -0.1700
Data Index: 2473838 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #19