Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3242 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4792. Min Range: -7.4792
Max Act: 7.4792. Min Act: -0.1700
Data Index: 942640 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4792. Min Range: -7.4792
Max Act: 7.3542. Min Act: -0.1700
Data Index: 208251 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4792. Min Range: -7.4792
Max Act: 7.2917. Min Act: -0.1700
Data Index: 3193862 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4792. Min Range: -7.4792
Max Act: 7.1354. Min Act: -0.1700
Data Index: 8210207 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4792. Min Range: -7.4792
Max Act: 7.0729. Min Act: -0.1700
Data Index: 4269621 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4792. Min Range: -7.4792
Max Act: 7.0104. Min Act: -0.1700
Data Index: 1187893 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4792. Min Range: -7.4792
Max Act: 7.0417. Min Act: -0.1700
Data Index: 918670 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4792. Min Range: -7.4792
Max Act: 7.0104. Min Act: -0.1700
Data Index: 928538 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4792. Min Range: -7.4792
Max Act: 6.9792. Min Act: -0.1700
Data Index: 792700 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4792. Min Range: -7.4792
Max Act: 6.9792. Min Act: -0.1700
Data Index: 2298930 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4792. Min Range: -7.4792
Max Act: 6.9479. Min Act: -0.1700
Data Index: 2999791 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4792. Min Range: -7.4792
Max Act: 6.9479. Min Act: -0.1700
Data Index: 6871214 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4792. Min Range: -7.4792
Max Act: 6.8854. Min Act: -0.1700
Data Index: 249930 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4792. Min Range: -7.4792
Max Act: 6.8542. Min Act: -0.1700
Data Index: 3745176 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4792. Min Range: -7.4792
Max Act: 6.8542. Min Act: -0.1700
Data Index: 5076950 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4792. Min Range: -7.4792
Max Act: 6.7917. Min Act: -0.1700
Data Index: 7299367 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4792. Min Range: -7.4792
Max Act: 6.8229. Min Act: -0.1700
Data Index: 8382281 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4792. Min Range: -7.4792
Max Act: 6.8542. Min Act: -0.1700
Data Index: 3080705 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4792. Min Range: -7.4792
Max Act: 6.8229. Min Act: -0.1700
Data Index: 6253852 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4792. Min Range: -7.4792
Max Act: 6.7604. Min Act: -0.1700
Data Index: 3027887 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #19