Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1826 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8502. Min Range: -5.8502
Max Act: 5.8502. Min Act: -0.1700
Data Index: 6723103 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8502. Min Range: -5.8502
Max Act: 5.8189. Min Act: -0.1700
Data Index: 7191051 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8502. Min Range: -5.8502
Max Act: 5.7564. Min Act: -0.1700
Data Index: 2260000 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8502. Min Range: -5.8502
Max Act: 5.6627. Min Act: -0.1700
Data Index: 7729711 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8502. Min Range: -5.8502
Max Act: 5.6627. Min Act: -0.1700
Data Index: 954112 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8502. Min Range: -5.8502
Max Act: 5.6939. Min Act: -0.1700
Data Index: 2010070 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8502. Min Range: -5.8502
Max Act: 5.6627. Min Act: -0.1700
Data Index: 1849462 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8502. Min Range: -5.8502
Max Act: 5.6002. Min Act: -0.1700
Data Index: 1887342 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8502. Min Range: -5.8502
Max Act: 5.6002. Min Act: -0.1700
Data Index: 230866 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8502. Min Range: -5.8502
Max Act: 5.6314. Min Act: -0.1700
Data Index: 7645877 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8502. Min Range: -5.8502
Max Act: 5.6314. Min Act: -0.1700
Data Index: 8118056 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8502. Min Range: -5.8502
Max Act: 5.5689. Min Act: -0.1700
Data Index: 1328160 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8502. Min Range: -5.8502
Max Act: 5.5377. Min Act: -0.1700
Data Index: 2493178 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8502. Min Range: -5.8502
Max Act: 5.5064. Min Act: -0.1700
Data Index: 1305836 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8502. Min Range: -5.8502
Max Act: 5.5377. Min Act: -0.1700
Data Index: 8606676 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8502. Min Range: -5.8502
Max Act: 5.5377. Min Act: -0.1700
Data Index: 6028448 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8502. Min Range: -5.8502
Max Act: 5.5377. Min Act: -0.1700
Data Index: 1137965 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8502. Min Range: -5.8502
Max Act: 5.5064. Min Act: -0.1700
Data Index: 8101584 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8502. Min Range: -5.8502
Max Act: 5.5064. Min Act: -0.1700
Data Index: 4742370 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8502. Min Range: -5.8502
Max Act: 5.5064. Min Act: -0.1700
Data Index: 256377 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #19