Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5528 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3178. Min Range: -7.3178
Max Act: 7.3178. Min Act: -0.1700
Data Index: 4439347 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3178. Min Range: -7.3178
Max Act: 7.2553. Min Act: -0.1700
Data Index: 2707092 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3178. Min Range: -7.3178
Max Act: 7.0678. Min Act: -0.1700
Data Index: 7979943 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3178. Min Range: -7.3178
Max Act: 7.0366. Min Act: -0.1700
Data Index: 5674565 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3178. Min Range: -7.3178
Max Act: 6.9741. Min Act: -0.1700
Data Index: 8591591 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3178. Min Range: -7.3178
Max Act: 6.9428. Min Act: -0.1700
Data Index: 6386427 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3178. Min Range: -7.3178
Max Act: 6.9116. Min Act: -0.1700
Data Index: 4718879 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3178. Min Range: -7.3178
Max Act: 6.8491. Min Act: -0.1700
Data Index: 1007996 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3178. Min Range: -7.3178
Max Act: 6.8178. Min Act: -0.1700
Data Index: 3073502 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3178. Min Range: -7.3178
Max Act: 6.7866. Min Act: -0.1700
Data Index: 7215210 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3178. Min Range: -7.3178
Max Act: 6.7241. Min Act: -0.1700
Data Index: 2343368 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3178. Min Range: -7.3178
Max Act: 6.6303. Min Act: -0.1700
Data Index: 6282484 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3178. Min Range: -7.3178
Max Act: 6.6928. Min Act: -0.1700
Data Index: 7330226 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3178. Min Range: -7.3178
Max Act: 6.6303. Min Act: -0.1700
Data Index: 7011405 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3178. Min Range: -7.3178
Max Act: 6.6303. Min Act: -0.1700
Data Index: 8784923 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3178. Min Range: -7.3178
Max Act: 6.6303. Min Act: -0.1700
Data Index: 3478111 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3178. Min Range: -7.3178
Max Act: 6.6303. Min Act: -0.1700
Data Index: 635775 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3178. Min Range: -7.3178
Max Act: 6.5991. Min Act: -0.1700
Data Index: 1988932 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3178. Min Range: -7.3178
Max Act: 6.5678. Min Act: -0.1700
Data Index: 7895967 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3178. Min Range: -7.3178
Max Act: 6.5366. Min Act: -0.1700
Data Index: 3850181 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #19