Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1002 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1717. Min Range: -6.1717
Max Act: 6.1717. Min Act: -0.1700
Data Index: 4226553 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1717. Min Range: -6.1717
Max Act: 6.0467. Min Act: -0.1700
Data Index: 1322516 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1717. Min Range: -6.1717
Max Act: 5.8279. Min Act: -0.1700
Data Index: 225355 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1717. Min Range: -6.1717
Max Act: 5.7654. Min Act: -0.1700
Data Index: 1805538 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1717. Min Range: -6.1717
Max Act: 5.7654. Min Act: -0.1700
Data Index: 5004635 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1717. Min Range: -6.1717
Max Act: 5.6717. Min Act: -0.1700
Data Index: 8174198 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1717. Min Range: -6.1717
Max Act: 5.6717. Min Act: -0.1700
Data Index: 2547217 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1717. Min Range: -6.1717
Max Act: 5.6404. Min Act: -0.1700
Data Index: 814521 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1717. Min Range: -6.1717
Max Act: 5.6404. Min Act: -0.1700
Data Index: 1943671 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1717. Min Range: -6.1717
Max Act: 5.6092. Min Act: -0.1700
Data Index: 5940385 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1717. Min Range: -6.1717
Max Act: 5.6092. Min Act: -0.1700
Data Index: 6080642 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1717. Min Range: -6.1717
Max Act: 5.5467. Min Act: -0.1700
Data Index: 1584797 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1717. Min Range: -6.1717
Max Act: 5.5467. Min Act: -0.1700
Data Index: 4658577 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1717. Min Range: -6.1717
Max Act: 5.5779. Min Act: -0.1700
Data Index: 7024492 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1717. Min Range: -6.1717
Max Act: 5.4842. Min Act: -0.1700
Data Index: 4476974 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1717. Min Range: -6.1717
Max Act: 5.4529. Min Act: -0.1700
Data Index: 15686 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1717. Min Range: -6.1717
Max Act: 5.4529. Min Act: -0.1700
Data Index: 4140610 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1717. Min Range: -6.1717
Max Act: 5.4529. Min Act: -0.1700
Data Index: 8034008 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1717. Min Range: -6.1717
Max Act: 5.3904. Min Act: -0.1700
Data Index: 6282677 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1717. Min Range: -6.1717
Max Act: 5.3904. Min Act: -0.1700
Data Index: 5358318 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #19