Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3816 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2790. Min Range: -7.2790
Max Act: 7.2790. Min Act: -0.1700
Data Index: 7978313 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2790. Min Range: -7.2790
Max Act: 7.2790. Min Act: -0.1700
Data Index: 4756893 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2790. Min Range: -7.2790
Max Act: 7.0290. Min Act: -0.1700
Data Index: 7200280 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2790. Min Range: -7.2790
Max Act: 6.9977. Min Act: -0.1700
Data Index: 2851162 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2790. Min Range: -7.2790
Max Act: 6.9352. Min Act: -0.1700
Data Index: 3190417 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2790. Min Range: -7.2790
Max Act: 6.9040. Min Act: -0.1700
Data Index: 886107 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2790. Min Range: -7.2790
Max Act: 6.8727. Min Act: -0.1700
Data Index: 7087329 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2790. Min Range: -7.2790
Max Act: 6.9040. Min Act: -0.1700
Data Index: 1425917 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2790. Min Range: -7.2790
Max Act: 6.7790. Min Act: -0.1700
Data Index: 5811908 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2790. Min Range: -7.2790
Max Act: 6.7477. Min Act: -0.1700
Data Index: 908627 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2790. Min Range: -7.2790
Max Act: 6.6540. Min Act: -0.1700
Data Index: 4948280 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2790. Min Range: -7.2790
Max Act: 6.6852. Min Act: -0.1700
Data Index: 4954134 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2790. Min Range: -7.2790
Max Act: 6.6852. Min Act: -0.1700
Data Index: 4337629 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2790. Min Range: -7.2790
Max Act: 6.6540. Min Act: -0.1700
Data Index: 448447 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2790. Min Range: -7.2790
Max Act: 6.6852. Min Act: -0.1700
Data Index: 2539042 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2790. Min Range: -7.2790
Max Act: 6.6540. Min Act: -0.1700
Data Index: 8092089 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2790. Min Range: -7.2790
Max Act: 6.6540. Min Act: -0.1700
Data Index: 1260779 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2790. Min Range: -7.2790
Max Act: 6.6227. Min Act: -0.1700
Data Index: 5839323 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2790. Min Range: -7.2790
Max Act: 6.6227. Min Act: -0.1700
Data Index: 3600047 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2790. Min Range: -7.2790
Max Act: 6.6227. Min Act: -0.1700
Data Index: 1999822 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #19