Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 796 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4648. Min Range: -6.4648
Max Act: 6.4648. Min Act: -0.1700
Data Index: 5381180 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4648. Min Range: -6.4648
Max Act: 6.4648. Min Act: -0.1700
Data Index: 8365085 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4648. Min Range: -6.4648
Max Act: 6.4335. Min Act: -0.1699
Data Index: 2679159 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4648. Min Range: -6.4648
Max Act: 6.3710. Min Act: -0.1700
Data Index: 31353 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4648. Min Range: -6.4648
Max Act: 6.4023. Min Act: -0.1699
Data Index: 3643709 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4648. Min Range: -6.4648
Max Act: 6.3710. Min Act: -0.1700
Data Index: 7537208 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4648. Min Range: -6.4648
Max Act: 6.3710. Min Act: -0.1700
Data Index: 8503048 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4648. Min Range: -6.4648
Max Act: 6.3710. Min Act: -0.1700
Data Index: 3684346 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4648. Min Range: -6.4648
Max Act: 6.3398. Min Act: -0.1700
Data Index: 8123108 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4648. Min Range: -6.4648
Max Act: 6.3398. Min Act: -0.1700
Data Index: 1458245 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4648. Min Range: -6.4648
Max Act: 6.3398. Min Act: -0.1699
Data Index: 5326791 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4648. Min Range: -6.4648
Max Act: 6.3398. Min Act: -0.1700
Data Index: 7008517 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4648. Min Range: -6.4648
Max Act: 6.3398. Min Act: -0.1700
Data Index: 6440393 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4648. Min Range: -6.4648
Max Act: 6.3085. Min Act: -0.1700
Data Index: 4264392 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4648. Min Range: -6.4648
Max Act: 6.3085. Min Act: -0.1700
Data Index: 5099464 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4648. Min Range: -6.4648
Max Act: 6.3085. Min Act: -0.1700
Data Index: 8116312 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4648. Min Range: -6.4648
Max Act: 6.3085. Min Act: -0.1700
Data Index: 8241245 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4648. Min Range: -6.4648
Max Act: 6.3085. Min Act: -0.1700
Data Index: 1748750 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4648. Min Range: -6.4648
Max Act: 6.3085. Min Act: -0.1700
Data Index: 3732809 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4648. Min Range: -6.4648
Max Act: 6.3085. Min Act: -0.1700
Data Index: 993937 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #19