Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2831 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9301. Min Range: -4.9301
Max Act: 4.9301. Min Act: -0.1700
Data Index: 5480854 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9301. Min Range: -4.9301
Max Act: 4.8051. Min Act: -0.1700
Data Index: 8105399 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9301. Min Range: -4.9301
Max Act: 4.8051. Min Act: -0.1700
Data Index: 8611124 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9301. Min Range: -4.9301
Max Act: 4.8051. Min Act: -0.1700
Data Index: 6432235 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9301. Min Range: -4.9301
Max Act: 4.7738. Min Act: -0.1700
Data Index: 429894 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9301. Min Range: -4.9301
Max Act: 4.7738. Min Act: -0.1700
Data Index: 7929343 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9301. Min Range: -4.9301
Max Act: 4.7426. Min Act: -0.1700
Data Index: 647817 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9301. Min Range: -4.9301
Max Act: 4.7426. Min Act: -0.1700
Data Index: 6494755 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9301. Min Range: -4.9301
Max Act: 4.7113. Min Act: -0.1700
Data Index: 4483423 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9301. Min Range: -4.9301
Max Act: 4.7113. Min Act: -0.1700
Data Index: 3314439 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9301. Min Range: -4.9301
Max Act: 4.7113. Min Act: -0.1700
Data Index: 6590492 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9301. Min Range: -4.9301
Max Act: 4.7113. Min Act: -0.1700
Data Index: 1752375 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9301. Min Range: -4.9301
Max Act: 4.6801. Min Act: -0.1700
Data Index: 7702886 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9301. Min Range: -4.9301
Max Act: 4.6801. Min Act: -0.1700
Data Index: 7591951 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9301. Min Range: -4.9301
Max Act: 4.6801. Min Act: -0.1700
Data Index: 4075010 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9301. Min Range: -4.9301
Max Act: 4.6801. Min Act: -0.1700
Data Index: 2063258 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9301. Min Range: -4.9301
Max Act: 4.6801. Min Act: -0.1700
Data Index: 299782 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9301. Min Range: -4.9301
Max Act: 4.6801. Min Act: -0.1700
Data Index: 7519680 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9301. Min Range: -4.9301
Max Act: 4.6801. Min Act: -0.1700
Data Index: 5901452 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9301. Min Range: -4.9301
Max Act: 4.6488. Min Act: -0.1700
Data Index: 7403076 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #19