Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1365 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8754. Min Range: -4.8754
Max Act: 4.8754. Min Act: -0.1700
Data Index: 966250 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8754. Min Range: -4.8754
Max Act: 4.8441. Min Act: -0.1700
Data Index: 815768 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8754. Min Range: -4.8754
Max Act: 4.7191. Min Act: -0.1700
Data Index: 6412778 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8754. Min Range: -4.8754
Max Act: 4.6879. Min Act: -0.1700
Data Index: 5168480 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8754. Min Range: -4.8754
Max Act: 4.6879. Min Act: -0.1700
Data Index: 1719992 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8754. Min Range: -4.8754
Max Act: 4.6879. Min Act: -0.1700
Data Index: 6300268 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8754. Min Range: -4.8754
Max Act: 4.6566. Min Act: -0.1700
Data Index: 1358578 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8754. Min Range: -4.8754
Max Act: 4.5941. Min Act: -0.1700
Data Index: 7198325 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8754. Min Range: -4.8754
Max Act: 4.5941. Min Act: -0.1700
Data Index: 4160895 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8754. Min Range: -4.8754
Max Act: 4.5941. Min Act: -0.1700
Data Index: 650091 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8754. Min Range: -4.8754
Max Act: 4.5941. Min Act: -0.1700
Data Index: 5090610 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8754. Min Range: -4.8754
Max Act: 4.6253. Min Act: -0.1700
Data Index: 3836480 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8754. Min Range: -4.8754
Max Act: 4.5628. Min Act: -0.1700
Data Index: 5425465 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8754. Min Range: -4.8754
Max Act: 4.5628. Min Act: -0.1700
Data Index: 1928302 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8754. Min Range: -4.8754
Max Act: 4.5628. Min Act: -0.1700
Data Index: 882006 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8754. Min Range: -4.8754
Max Act: 4.5316. Min Act: -0.1700
Data Index: 1740668 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8754. Min Range: -4.8754
Max Act: 4.5003. Min Act: -0.1700
Data Index: 35693 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8754. Min Range: -4.8754
Max Act: 4.5316. Min Act: -0.1700
Data Index: 1141665 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8754. Min Range: -4.8754
Max Act: 4.5316. Min Act: -0.1700
Data Index: 2076460 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8754. Min Range: -4.8754
Max Act: 4.5316. Min Act: -0.1700
Data Index: 3462564 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #19