Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3233 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3398. Min Range: -8.3398
Max Act: 8.3398. Min Act: -0.1700
Data Index: 493182 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3398. Min Range: -8.3398
Max Act: 8.2148. Min Act: -0.1700
Data Index: 6890100 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3398. Min Range: -8.3398
Max Act: 8.1523. Min Act: -0.1700
Data Index: 8525714 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3398. Min Range: -8.3398
Max Act: 8.0898. Min Act: -0.1700
Data Index: 6325807 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3398. Min Range: -8.3398
Max Act: 8.0898. Min Act: -0.1700
Data Index: 6393465 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3398. Min Range: -8.3398
Max Act: 8.1523. Min Act: -0.1700
Data Index: 4618608 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3398. Min Range: -8.3398
Max Act: 8.0273. Min Act: -0.1700
Data Index: 1270797 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3398. Min Range: -8.3398
Max Act: 7.9648. Min Act: -0.1700
Data Index: 1612569 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3398. Min Range: -8.3398
Max Act: 7.9648. Min Act: -0.1700
Data Index: 6300600 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3398. Min Range: -8.3398
Max Act: 7.9648. Min Act: -0.1700
Data Index: 8016496 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3398. Min Range: -8.3398
Max Act: 7.9648. Min Act: -0.1700
Data Index: 7036162 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3398. Min Range: -8.3398
Max Act: 7.9648. Min Act: -0.1700
Data Index: 5341438 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3398. Min Range: -8.3398
Max Act: 7.9023. Min Act: -0.1700
Data Index: 3110871 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3398. Min Range: -8.3398
Max Act: 7.9023. Min Act: -0.1700
Data Index: 5466189 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3398. Min Range: -8.3398
Max Act: 7.9023. Min Act: -0.1700
Data Index: 7855110 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3398. Min Range: -8.3398
Max Act: 7.9023. Min Act: -0.1700
Data Index: 8240966 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3398. Min Range: -8.3398
Max Act: 7.9648. Min Act: -0.1700
Data Index: 2199123 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3398. Min Range: -8.3398
Max Act: 7.8398. Min Act: -0.1700
Data Index: 7784333 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3398. Min Range: -8.3398
Max Act: 7.8398. Min Act: -0.1700
Data Index: 6886662 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3398. Min Range: -8.3398
Max Act: 7.8398. Min Act: -0.1700
Data Index: 3342057 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19