Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1411 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7825. Min Range: -7.7825
Max Act: 7.7825. Min Act: -0.1700
Data Index: 7977789 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7825. Min Range: -7.7825
Max Act: 6.9387. Min Act: -0.1700
Data Index: 2065496 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7825. Min Range: -7.7825
Max Act: 6.8450. Min Act: -0.1700
Data Index: 6410555 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7825. Min Range: -7.7825
Max Act: 6.8450. Min Act: -0.1700
Data Index: 1575935 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7825. Min Range: -7.7825
Max Act: 6.8450. Min Act: -0.1700
Data Index: 8159064 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7825. Min Range: -7.7825
Max Act: 6.7825. Min Act: -0.1700
Data Index: 3535646 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7825. Min Range: -7.7825
Max Act: 6.7200. Min Act: -0.1700
Data Index: 2860543 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7825. Min Range: -7.7825
Max Act: 6.6575. Min Act: -0.1700
Data Index: 4313398 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7825. Min Range: -7.7825
Max Act: 6.5950. Min Act: -0.1700
Data Index: 4517751 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7825. Min Range: -7.7825
Max Act: 6.5950. Min Act: -0.1700
Data Index: 6792071 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7825. Min Range: -7.7825
Max Act: 6.5950. Min Act: -0.1700
Data Index: 3484266 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7825. Min Range: -7.7825
Max Act: 6.5637. Min Act: -0.1700
Data Index: 5432176 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7825. Min Range: -7.7825
Max Act: 6.5637. Min Act: -0.1700
Data Index: 4941065 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7825. Min Range: -7.7825
Max Act: 6.5637. Min Act: -0.1700
Data Index: 2221812 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7825. Min Range: -7.7825
Max Act: 6.5325. Min Act: -0.1700
Data Index: 2634799 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7825. Min Range: -7.7825
Max Act: 6.5325. Min Act: -0.1700
Data Index: 2990810 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7825. Min Range: -7.7825
Max Act: 6.5012. Min Act: -0.1700
Data Index: 5995 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7825. Min Range: -7.7825
Max Act: 6.5325. Min Act: -0.1700
Data Index: 1322437 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7825. Min Range: -7.7825
Max Act: 6.5325. Min Act: -0.1700
Data Index: 7541750 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7825. Min Range: -7.7825
Max Act: 6.5012. Min Act: -0.1700
Data Index: 3346531 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #19