Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3541 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7754. Min Range: -6.7754
Max Act: 6.7754. Min Act: -0.1700
Data Index: 4395034 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7754. Min Range: -6.7754
Max Act: 6.7441. Min Act: -0.1700
Data Index: 3742406 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7754. Min Range: -6.7754
Max Act: 6.7129. Min Act: -0.1700
Data Index: 315725 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7754. Min Range: -6.7754
Max Act: 6.7129. Min Act: -0.1700
Data Index: 5664759 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7754. Min Range: -6.7754
Max Act: 6.6816. Min Act: -0.1700
Data Index: 2477123 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7754. Min Range: -6.7754
Max Act: 6.6816. Min Act: -0.1700
Data Index: 2476344 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7754. Min Range: -6.7754
Max Act: 6.6816. Min Act: -0.1700
Data Index: 6258366 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7754. Min Range: -6.7754
Max Act: 6.6191. Min Act: -0.1700
Data Index: 97330 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7754. Min Range: -6.7754
Max Act: 6.6504. Min Act: -0.1700
Data Index: 5230822 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7754. Min Range: -6.7754
Max Act: 6.6504. Min Act: -0.1700
Data Index: 6203704 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7754. Min Range: -6.7754
Max Act: 6.6191. Min Act: -0.1700
Data Index: 7237885 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7754. Min Range: -6.7754
Max Act: 6.5879. Min Act: -0.1700
Data Index: 7848950 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7754. Min Range: -6.7754
Max Act: 6.6191. Min Act: -0.1700
Data Index: 127308 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7754. Min Range: -6.7754
Max Act: 6.6191. Min Act: -0.1700
Data Index: 2815605 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7754. Min Range: -6.7754
Max Act: 6.5879. Min Act: -0.1700
Data Index: 5726317 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7754. Min Range: -6.7754
Max Act: 6.5879. Min Act: -0.1700
Data Index: 3656708 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7754. Min Range: -6.7754
Max Act: 6.5566. Min Act: -0.1700
Data Index: 2148693 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7754. Min Range: -6.7754
Max Act: 6.5879. Min Act: -0.1700
Data Index: 4501819 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7754. Min Range: -6.7754
Max Act: 6.5566. Min Act: -0.1700
Data Index: 3060237 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7754. Min Range: -6.7754
Max Act: 6.5254. Min Act: -0.1700
Data Index: 488300 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #19