Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5613 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5616. Min Range: -5.5616
Max Act: 5.5616. Min Act: -0.1700
Data Index: 6768355 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5616. Min Range: -5.5616
Max Act: 5.4991. Min Act: -0.1700
Data Index: 3804199 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5616. Min Range: -5.5616
Max Act: 5.4991. Min Act: -0.1700
Data Index: 249342 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5616. Min Range: -5.5616
Max Act: 5.4678. Min Act: -0.1700
Data Index: 5998695 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5616. Min Range: -5.5616
Max Act: 5.4991. Min Act: -0.1700
Data Index: 1753436 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5616. Min Range: -5.5616
Max Act: 5.4678. Min Act: -0.1700
Data Index: 2751115 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5616. Min Range: -5.5616
Max Act: 5.4366. Min Act: -0.1700
Data Index: 3254401 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5616. Min Range: -5.5616
Max Act: 5.4053. Min Act: -0.1700
Data Index: 7670336 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5616. Min Range: -5.5616
Max Act: 5.3741. Min Act: -0.1700
Data Index: 6230101 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5616. Min Range: -5.5616
Max Act: 5.4053. Min Act: -0.1700
Data Index: 3023284 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5616. Min Range: -5.5616
Max Act: 5.3741. Min Act: -0.1700
Data Index: 3801032 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5616. Min Range: -5.5616
Max Act: 5.4053. Min Act: -0.1700
Data Index: 2946037 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5616. Min Range: -5.5616
Max Act: 5.3428. Min Act: -0.1700
Data Index: 2502715 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5616. Min Range: -5.5616
Max Act: 5.3428. Min Act: -0.1700
Data Index: 3948065 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5616. Min Range: -5.5616
Max Act: 5.3428. Min Act: -0.1700
Data Index: 109786 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5616. Min Range: -5.5616
Max Act: 5.3116. Min Act: -0.1700
Data Index: 2985734 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5616. Min Range: -5.5616
Max Act: 5.3116. Min Act: -0.1700
Data Index: 673816 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5616. Min Range: -5.5616
Max Act: 5.2803. Min Act: -0.1700
Data Index: 4825219 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5616. Min Range: -5.5616
Max Act: 5.3116. Min Act: -0.1700
Data Index: 6230100 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5616. Min Range: -5.5616
Max Act: 5.2803. Min Act: -0.1700
Data Index: 3728232 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #19