Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2906 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0577. Min Range: -7.0577
Max Act: 7.0577. Min Act: -0.1700
Data Index: 904508 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0577. Min Range: -7.0577
Max Act: 6.7452. Min Act: -0.1700
Data Index: 7866980 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0577. Min Range: -7.0577
Max Act: 6.7765. Min Act: -0.1700
Data Index: 3502097 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0577. Min Range: -7.0577
Max Act: 6.7452. Min Act: -0.1700
Data Index: 8680916 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0577. Min Range: -7.0577
Max Act: 6.7452. Min Act: -0.1700
Data Index: 7782866 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0577. Min Range: -7.0577
Max Act: 6.7140. Min Act: -0.1700
Data Index: 7347332 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0577. Min Range: -7.0577
Max Act: 6.7140. Min Act: -0.1700
Data Index: 1688174 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0577. Min Range: -7.0577
Max Act: 6.6827. Min Act: -0.1700
Data Index: 8141727 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0577. Min Range: -7.0577
Max Act: 6.6827. Min Act: -0.1700
Data Index: 7088944 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0577. Min Range: -7.0577
Max Act: 6.6515. Min Act: -0.1700
Data Index: 6527444 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0577. Min Range: -7.0577
Max Act: 6.6827. Min Act: -0.1700
Data Index: 605175 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0577. Min Range: -7.0577
Max Act: 6.6515. Min Act: -0.1700
Data Index: 2785504 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0577. Min Range: -7.0577
Max Act: 6.6515. Min Act: -0.1700
Data Index: 6181866 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0577. Min Range: -7.0577
Max Act: 6.6202. Min Act: -0.1700
Data Index: 6279321 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0577. Min Range: -7.0577
Max Act: 6.6202. Min Act: -0.1700
Data Index: 904507 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0577. Min Range: -7.0577
Max Act: 6.6202. Min Act: -0.1700
Data Index: 1758082 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0577. Min Range: -7.0577
Max Act: 6.6202. Min Act: -0.1700
Data Index: 4608857 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0577. Min Range: -7.0577
Max Act: 6.6515. Min Act: -0.1700
Data Index: 2221576 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0577. Min Range: -7.0577
Max Act: 6.6202. Min Act: -0.1700
Data Index: 4655231 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0577. Min Range: -7.0577
Max Act: 6.5890. Min Act: -0.1700
Data Index: 1926109 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #19