Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2551 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8357. Min Range: -5.8357
Max Act: 5.8357. Min Act: -0.1700
Data Index: 4884380 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8357. Min Range: -5.8357
Max Act: 5.7419. Min Act: -0.1700
Data Index: 195449 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8357. Min Range: -5.8357
Max Act: 5.6794. Min Act: -0.1700
Data Index: 5755683 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8357. Min Range: -5.8357
Max Act: 5.6794. Min Act: -0.1700
Data Index: 2060211 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8357. Min Range: -5.8357
Max Act: 5.6482. Min Act: -0.1700
Data Index: 3873960 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8357. Min Range: -5.8357
Max Act: 5.6482. Min Act: -0.1700
Data Index: 6520798 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8357. Min Range: -5.8357
Max Act: 5.6169. Min Act: -0.1700
Data Index: 4872358 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8357. Min Range: -5.8357
Max Act: 5.6169. Min Act: -0.1700
Data Index: 2046342 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8357. Min Range: -5.8357
Max Act: 5.6169. Min Act: -0.1700
Data Index: 5973207 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8357. Min Range: -5.8357
Max Act: 5.6169. Min Act: -0.1700
Data Index: 8818117 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8357. Min Range: -5.8357
Max Act: 5.6482. Min Act: -0.1700
Data Index: 3737177 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8357. Min Range: -5.8357
Max Act: 5.5857. Min Act: -0.1700
Data Index: 4704639 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8357. Min Range: -5.8357
Max Act: 5.5857. Min Act: -0.1700
Data Index: 6588872 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8357. Min Range: -5.8357
Max Act: 5.5857. Min Act: -0.1700
Data Index: 2136717 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8357. Min Range: -5.8357
Max Act: 5.5544. Min Act: -0.1700
Data Index: 279332 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8357. Min Range: -5.8357
Max Act: 5.5544. Min Act: -0.1700
Data Index: 4476709 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8357. Min Range: -5.8357
Max Act: 5.5857. Min Act: -0.1700
Data Index: 4049790 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8357. Min Range: -5.8357
Max Act: 5.5232. Min Act: -0.1700
Data Index: 2732270 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8357. Min Range: -5.8357
Max Act: 5.5544. Min Act: -0.1700
Data Index: 5471545 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8357. Min Range: -5.8357
Max Act: 5.4919. Min Act: -0.1700
Data Index: 5582046 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #19