Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1156 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3579. Min Range: -6.3579
Max Act: 6.3579. Min Act: -0.1700
Data Index: 1254674 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3579. Min Range: -6.3579
Max Act: 6.2329. Min Act: -0.1700
Data Index: 5600262 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3579. Min Range: -6.3579
Max Act: 6.2329. Min Act: -0.1699
Data Index: 7708738 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3579. Min Range: -6.3579
Max Act: 6.2329. Min Act: -0.1700
Data Index: 4400218 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3579. Min Range: -6.3579
Max Act: 6.2017. Min Act: -0.1700
Data Index: 4879316 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3579. Min Range: -6.3579
Max Act: 6.1392. Min Act: -0.1700
Data Index: 8625175 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3579. Min Range: -6.3579
Max Act: 6.1392. Min Act: -0.1700
Data Index: 7881244 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3579. Min Range: -6.3579
Max Act: 6.1392. Min Act: -0.1700
Data Index: 7507791 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3579. Min Range: -6.3579
Max Act: 6.1392. Min Act: -0.1700
Data Index: 7752121 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3579. Min Range: -6.3579
Max Act: 6.0767. Min Act: -0.1699
Data Index: 7947952 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3579. Min Range: -6.3579
Max Act: 6.0454. Min Act: -0.1700
Data Index: 1592613 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3579. Min Range: -6.3579
Max Act: 6.0454. Min Act: -0.1700
Data Index: 882920 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3579. Min Range: -6.3579
Max Act: 6.0142. Min Act: -0.1700
Data Index: 4944608 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3579. Min Range: -6.3579
Max Act: 6.0142. Min Act: -0.1700
Data Index: 8801391 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3579. Min Range: -6.3579
Max Act: 5.9829. Min Act: -0.1699
Data Index: 1490949 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3579. Min Range: -6.3579
Max Act: 5.9517. Min Act: -0.1700
Data Index: 8692475 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3579. Min Range: -6.3579
Max Act: 5.9204. Min Act: -0.1695
Data Index: 755409 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3579. Min Range: -6.3579
Max Act: 5.9204. Min Act: -0.1699
Data Index: 8361883 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3579. Min Range: -6.3579
Max Act: 5.9204. Min Act: -0.1700
Data Index: 8321471 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3579. Min Range: -6.3579
Max Act: 5.9204. Min Act: -0.1700
Data Index: 5787605 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #19