Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3665 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1908. Min Range: -6.1908
Max Act: 6.1908. Min Act: -0.1700
Data Index: 8019822 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1908. Min Range: -6.1908
Max Act: 5.9720. Min Act: -0.1700
Data Index: 5374830 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1908. Min Range: -6.1908
Max Act: 6.0033. Min Act: -0.1700
Data Index: 8333197 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1908. Min Range: -6.1908
Max Act: 5.8470. Min Act: -0.1700
Data Index: 7578121 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1908. Min Range: -6.1908
Max Act: 5.8783. Min Act: -0.1700
Data Index: 2571739 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1908. Min Range: -6.1908
Max Act: 5.8470. Min Act: -0.1700
Data Index: 6016426 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1908. Min Range: -6.1908
Max Act: 5.8783. Min Act: -0.1700
Data Index: 7415803 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1908. Min Range: -6.1908
Max Act: 5.8470. Min Act: -0.1700
Data Index: 6783532 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1908. Min Range: -6.1908
Max Act: 5.8158. Min Act: -0.1700
Data Index: 1998603 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1908. Min Range: -6.1908
Max Act: 5.7845. Min Act: -0.1700
Data Index: 5942799 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1908. Min Range: -6.1908
Max Act: 5.7533. Min Act: -0.1700
Data Index: 1175861 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1908. Min Range: -6.1908
Max Act: 5.7533. Min Act: -0.1700
Data Index: 4884520 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1908. Min Range: -6.1908
Max Act: 5.6908. Min Act: -0.1700
Data Index: 296616 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1908. Min Range: -6.1908
Max Act: 5.6908. Min Act: -0.1700
Data Index: 7489025 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1908. Min Range: -6.1908
Max Act: 5.6595. Min Act: -0.1700
Data Index: 4839730 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1908. Min Range: -6.1908
Max Act: 5.6595. Min Act: -0.1700
Data Index: 3931142 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1908. Min Range: -6.1908
Max Act: 5.6595. Min Act: -0.1700
Data Index: 3073982 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1908. Min Range: -6.1908
Max Act: 5.6595. Min Act: -0.1700
Data Index: 6798126 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1908. Min Range: -6.1908
Max Act: 5.6283. Min Act: -0.1700
Data Index: 8490690 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1908. Min Range: -6.1908
Max Act: 5.6283. Min Act: -0.1700
Data Index: 3200519 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #19