Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2689 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5777. Min Range: -7.5777
Max Act: 7.5777. Min Act: -0.1700
Data Index: 1680286 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5777. Min Range: -7.5777
Max Act: 7.3277. Min Act: -0.1700
Data Index: 917535 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5777. Min Range: -7.5777
Max Act: 7.0777. Min Act: -0.1700
Data Index: 4421078 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5777. Min Range: -7.5777
Max Act: 7.0464. Min Act: -0.1700
Data Index: 2239034 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5777. Min Range: -7.5777
Max Act: 7.0464. Min Act: -0.1700
Data Index: 3982075 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5777. Min Range: -7.5777
Max Act: 7.0464. Min Act: -0.1700
Data Index: 4527765 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5777. Min Range: -7.5777
Max Act: 7.0152. Min Act: -0.1700
Data Index: 6568759 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5777. Min Range: -7.5777
Max Act: 6.9839. Min Act: -0.1700
Data Index: 8752765 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5777. Min Range: -7.5777
Max Act: 6.9214. Min Act: -0.1700
Data Index: 6248342 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5777. Min Range: -7.5777
Max Act: 6.9214. Min Act: -0.1700
Data Index: 6954960 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5777. Min Range: -7.5777
Max Act: 6.8902. Min Act: -0.1700
Data Index: 7466926 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5777. Min Range: -7.5777
Max Act: 6.8902. Min Act: -0.1700
Data Index: 3417269 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5777. Min Range: -7.5777
Max Act: 6.8589. Min Act: -0.1700
Data Index: 8225574 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5777. Min Range: -7.5777
Max Act: 6.8589. Min Act: -0.1700
Data Index: 1090030 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5777. Min Range: -7.5777
Max Act: 6.8277. Min Act: -0.1700
Data Index: 1153625 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5777. Min Range: -7.5777
Max Act: 6.8277. Min Act: -0.1700
Data Index: 8561735 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5777. Min Range: -7.5777
Max Act: 6.7964. Min Act: -0.1700
Data Index: 280013 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5777. Min Range: -7.5777
Max Act: 6.7964. Min Act: -0.1700
Data Index: 6900859 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5777. Min Range: -7.5777
Max Act: 6.7964. Min Act: -0.1700
Data Index: 8000629 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5777. Min Range: -7.5777
Max Act: 6.7652. Min Act: -0.1700
Data Index: 7174857 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #19