Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 811 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9035. Min Range: -6.9035
Max Act: 6.9035. Min Act: -0.1700
Data Index: 2502066 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9035. Min Range: -6.9035
Max Act: 6.7160. Min Act: -0.1700
Data Index: 2924134 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9035. Min Range: -6.9035
Max Act: 6.6222. Min Act: -0.1700
Data Index: 4118266 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9035. Min Range: -6.9035
Max Act: 6.5910. Min Act: -0.1700
Data Index: 8506513 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9035. Min Range: -6.9035
Max Act: 6.6222. Min Act: -0.1700
Data Index: 6816126 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9035. Min Range: -6.9035
Max Act: 6.5597. Min Act: -0.1700
Data Index: 1849494 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9035. Min Range: -6.9035
Max Act: 6.4660. Min Act: -0.1700
Data Index: 3605911 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9035. Min Range: -6.9035
Max Act: 6.4660. Min Act: -0.1700
Data Index: 402740 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9035. Min Range: -6.9035
Max Act: 6.4347. Min Act: -0.1700
Data Index: 5607166 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9035. Min Range: -6.9035
Max Act: 6.4347. Min Act: -0.1700
Data Index: 5478134 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9035. Min Range: -6.9035
Max Act: 6.4035. Min Act: -0.1700
Data Index: 701778 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9035. Min Range: -6.9035
Max Act: 6.3410. Min Act: -0.1700
Data Index: 4687181 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9035. Min Range: -6.9035
Max Act: 6.4035. Min Act: -0.1700
Data Index: 5793973 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9035. Min Range: -6.9035
Max Act: 6.3722. Min Act: -0.1700
Data Index: 7755744 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9035. Min Range: -6.9035
Max Act: 6.3410. Min Act: -0.1700
Data Index: 5412554 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9035. Min Range: -6.9035
Max Act: 6.3410. Min Act: -0.1700
Data Index: 3267325 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9035. Min Range: -6.9035
Max Act: 6.3722. Min Act: -0.1700
Data Index: 8284270 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9035. Min Range: -6.9035
Max Act: 6.3410. Min Act: -0.1700
Data Index: 8636300 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9035. Min Range: -6.9035
Max Act: 6.3097. Min Act: -0.1700
Data Index: 40930 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9035. Min Range: -6.9035
Max Act: 6.3097. Min Act: -0.1700
Data Index: 4537556 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19