Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3343 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1712. Min Range: -5.1712
Max Act: 5.1712. Min Act: -0.1700
Data Index: 1959873 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1712. Min Range: -5.1712
Max Act: 5.0150. Min Act: -0.1700
Data Index: 8757653 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1712. Min Range: -5.1712
Max Act: 5.0150. Min Act: -0.1700
Data Index: 4400621 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1712. Min Range: -5.1712
Max Act: 5.0150. Min Act: -0.1700
Data Index: 5200134 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1712. Min Range: -5.1712
Max Act: 4.9837. Min Act: -0.1700
Data Index: 1414266 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1712. Min Range: -5.1712
Max Act: 4.9837. Min Act: -0.1700
Data Index: 505453 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1712. Min Range: -5.1712
Max Act: 5.0150. Min Act: -0.1700
Data Index: 2958921 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1712. Min Range: -5.1712
Max Act: 4.9837. Min Act: -0.1700
Data Index: 4529929 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1712. Min Range: -5.1712
Max Act: 4.9837. Min Act: -0.1700
Data Index: 64229 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1712. Min Range: -5.1712
Max Act: 4.9837. Min Act: -0.1700
Data Index: 6963479 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1712. Min Range: -5.1712
Max Act: 4.9525. Min Act: -0.1700
Data Index: 4730061 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1712. Min Range: -5.1712
Max Act: 4.9212. Min Act: -0.1700
Data Index: 1217788 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1712. Min Range: -5.1712
Max Act: 4.9525. Min Act: -0.1700
Data Index: 2607931 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1712. Min Range: -5.1712
Max Act: 4.9525. Min Act: -0.1700
Data Index: 3756332 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1712. Min Range: -5.1712
Max Act: 4.9525. Min Act: -0.1700
Data Index: 351793 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1712. Min Range: -5.1712
Max Act: 4.9525. Min Act: -0.1700
Data Index: 6658752 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1712. Min Range: -5.1712
Max Act: 4.9525. Min Act: -0.1700
Data Index: 6186494 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1712. Min Range: -5.1712
Max Act: 4.9212. Min Act: -0.1700
Data Index: 1966945 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1712. Min Range: -5.1712
Max Act: 4.9525. Min Act: -0.1700
Data Index: 5817967 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1712. Min Range: -5.1712
Max Act: 4.9525. Min Act: -0.1700
Data Index: 504495 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #19