Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5560 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6378. Min Range: -8.6378
Max Act: 8.6378. Min Act: -0.1700
Data Index: 5409042 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6378. Min Range: -8.6378
Max Act: 8.3253. Min Act: -0.1700
Data Index: 4222068 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6378. Min Range: -8.6378
Max Act: 8.3253. Min Act: -0.1700
Data Index: 5686823 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6378. Min Range: -8.6378
Max Act: 8.2628. Min Act: -0.1700
Data Index: 2077704 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6378. Min Range: -8.6378
Max Act: 8.2003. Min Act: -0.1700
Data Index: 1645110 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6378. Min Range: -8.6378
Max Act: 8.2003. Min Act: -0.1700
Data Index: 2002199 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6378. Min Range: -8.6378
Max Act: 8.1066. Min Act: -0.1700
Data Index: 8409279 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6378. Min Range: -8.6378
Max Act: 8.0753. Min Act: -0.1700
Data Index: 4790609 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6378. Min Range: -8.6378
Max Act: 8.0128. Min Act: -0.1700
Data Index: 8596020 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6378. Min Range: -8.6378
Max Act: 8.0441. Min Act: -0.1700
Data Index: 6158588 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6378. Min Range: -8.6378
Max Act: 7.9191. Min Act: -0.1700
Data Index: 3717151 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6378. Min Range: -8.6378
Max Act: 7.8878. Min Act: -0.1700
Data Index: 2363863 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6378. Min Range: -8.6378
Max Act: 7.8878. Min Act: -0.1700
Data Index: 5632668 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6378. Min Range: -8.6378
Max Act: 7.7941. Min Act: -0.1700
Data Index: 1028411 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6378. Min Range: -8.6378
Max Act: 7.8253. Min Act: -0.1700
Data Index: 6199526 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6378. Min Range: -8.6378
Max Act: 7.7628. Min Act: -0.1700
Data Index: 2027258 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6378. Min Range: -8.6378
Max Act: 7.7316. Min Act: -0.1700
Data Index: 5476839 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6378. Min Range: -8.6378
Max Act: 7.7003. Min Act: -0.1700
Data Index: 5994168 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6378. Min Range: -8.6378
Max Act: 7.7316. Min Act: -0.1700
Data Index: 7814407 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6378. Min Range: -8.6378
Max Act: 7.6691. Min Act: -0.1700
Data Index: 4390686 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #19