Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4695 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5168. Min Range: -6.5168
Max Act: 6.5168. Min Act: -0.1700
Data Index: 8282456 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5168. Min Range: -6.5168
Max Act: 6.4543. Min Act: -0.1700
Data Index: 659062 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5168. Min Range: -6.5168
Max Act: 6.2356. Min Act: -0.1700
Data Index: 3163225 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5168. Min Range: -6.5168
Max Act: 6.2043. Min Act: -0.1700
Data Index: 4756031 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5168. Min Range: -6.5168
Max Act: 6.1731. Min Act: -0.1700
Data Index: 5407460 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5168. Min Range: -6.5168
Max Act: 6.1418. Min Act: -0.1700
Data Index: 6780084 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5168. Min Range: -6.5168
Max Act: 6.1418. Min Act: -0.1700
Data Index: 5369947 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5168. Min Range: -6.5168
Max Act: 6.1418. Min Act: -0.1700
Data Index: 2978893 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5168. Min Range: -6.5168
Max Act: 6.0793. Min Act: -0.1700
Data Index: 2785470 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5168. Min Range: -6.5168
Max Act: 6.0481. Min Act: -0.1700
Data Index: 8467695 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5168. Min Range: -6.5168
Max Act: 6.0481. Min Act: -0.1700
Data Index: 2924278 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5168. Min Range: -6.5168
Max Act: 6.0168. Min Act: -0.1700
Data Index: 3098603 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5168. Min Range: -6.5168
Max Act: 6.0168. Min Act: -0.1700
Data Index: 8147656 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5168. Min Range: -6.5168
Max Act: 6.0168. Min Act: -0.1700
Data Index: 4737340 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5168. Min Range: -6.5168
Max Act: 6.0168. Min Act: -0.1700
Data Index: 5563780 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5168. Min Range: -6.5168
Max Act: 6.0168. Min Act: -0.1700
Data Index: 4120479 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5168. Min Range: -6.5168
Max Act: 5.9543. Min Act: -0.1700
Data Index: 4524729 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5168. Min Range: -6.5168
Max Act: 5.9856. Min Act: -0.1700
Data Index: 7562402 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5168. Min Range: -6.5168
Max Act: 5.9856. Min Act: -0.1700
Data Index: 47709 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5168. Min Range: -6.5168
Max Act: 5.9856. Min Act: -0.1700
Data Index: 3082128 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #19