Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3383 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7704. Min Range: -4.7704
Max Act: 4.7704. Min Act: -0.1700
Data Index: 8100170 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7704. Min Range: -4.7704
Max Act: 4.7079. Min Act: -0.1700
Data Index: 7164294 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7704. Min Range: -4.7704
Max Act: 4.6142. Min Act: -0.1700
Data Index: 3098296 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7704. Min Range: -4.7704
Max Act: 4.5829. Min Act: -0.1700
Data Index: 6116181 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7704. Min Range: -4.7704
Max Act: 4.5516. Min Act: -0.1700
Data Index: 4730776 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7704. Min Range: -4.7704
Max Act: 4.5829. Min Act: -0.1700
Data Index: 2590485 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7704. Min Range: -4.7704
Max Act: 4.5516. Min Act: -0.1700
Data Index: 2960546 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7704. Min Range: -4.7704
Max Act: 4.5516. Min Act: -0.1700
Data Index: 4846518 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7704. Min Range: -4.7704
Max Act: 4.5829. Min Act: -0.1700
Data Index: 6008349 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7704. Min Range: -4.7704
Max Act: 4.5516. Min Act: -0.1700
Data Index: 1442554 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7704. Min Range: -4.7704
Max Act: 4.5204. Min Act: -0.1700
Data Index: 130595 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7704. Min Range: -4.7704
Max Act: 4.5204. Min Act: -0.1700
Data Index: 8351358 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7704. Min Range: -4.7704
Max Act: 4.4266. Min Act: -0.1700
Data Index: 8597768 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7704. Min Range: -4.7704
Max Act: 4.4891. Min Act: -0.1700
Data Index: 4540348 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7704. Min Range: -4.7704
Max Act: 4.4891. Min Act: -0.1700
Data Index: 7067004 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7704. Min Range: -4.7704
Max Act: 4.4891. Min Act: -0.1700
Data Index: 5708988 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7704. Min Range: -4.7704
Max Act: 4.4891. Min Act: -0.1700
Data Index: 6058072 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7704. Min Range: -4.7704
Max Act: 4.4579. Min Act: -0.1700
Data Index: 557689 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7704. Min Range: -4.7704
Max Act: 4.4891. Min Act: -0.1700
Data Index: 4457400 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7704. Min Range: -4.7704
Max Act: 4.4891. Min Act: -0.1700
Data Index: 6408787 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #19