Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2746 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6255. Min Range: -8.6255
Max Act: 8.6255. Min Act: -0.1700
Data Index: 5801257 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6255. Min Range: -8.6255
Max Act: 8.5630. Min Act: -0.1700
Data Index: 3100425 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6255. Min Range: -8.6255
Max Act: 8.3755. Min Act: -0.1700
Data Index: 3854601 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6255. Min Range: -8.6255
Max Act: 8.3755. Min Act: -0.1700
Data Index: 2055192 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6255. Min Range: -8.6255
Max Act: 8.2505. Min Act: -0.1700
Data Index: 8575617 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6255. Min Range: -8.6255
Max Act: 8.1568. Min Act: -0.1700
Data Index: 3897701 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6255. Min Range: -8.6255
Max Act: 8.1255. Min Act: -0.1700
Data Index: 5456758 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6255. Min Range: -8.6255
Max Act: 8.0005. Min Act: -0.1700
Data Index: 7050111 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6255. Min Range: -8.6255
Max Act: 8.0005. Min Act: -0.1700
Data Index: 1717984 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6255. Min Range: -8.6255
Max Act: 7.9693. Min Act: -0.1700
Data Index: 4238626 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6255. Min Range: -8.6255
Max Act: 7.9380. Min Act: -0.1700
Data Index: 2298696 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6255. Min Range: -8.6255
Max Act: 7.8755. Min Act: -0.1700
Data Index: 1701553 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6255. Min Range: -8.6255
Max Act: 7.8130. Min Act: -0.1700
Data Index: 5589449 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6255. Min Range: -8.6255
Max Act: 7.7818. Min Act: -0.1700
Data Index: 2477937 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6255. Min Range: -8.6255
Max Act: 7.7505. Min Act: -0.1700
Data Index: 4666995 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6255. Min Range: -8.6255
Max Act: 7.6880. Min Act: -0.1700
Data Index: 4546579 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6255. Min Range: -8.6255
Max Act: 7.7193. Min Act: -0.1700
Data Index: 5460131 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6255. Min Range: -8.6255
Max Act: 7.7193. Min Act: -0.1700
Data Index: 4664787 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6255. Min Range: -8.6255
Max Act: 7.6880. Min Act: -0.1699
Data Index: 8291050 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6255. Min Range: -8.6255
Max Act: 7.6568. Min Act: -0.1700
Data Index: 761970 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #19