Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3887 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6515. Min Range: -10.6515
Max Act: 10.6515. Min Act: -0.1700
Data Index: 3603178 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6515. Min Range: -10.6515
Max Act: 10.6515. Min Act: -0.1700
Data Index: 7853078 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6515. Min Range: -10.6515
Max Act: 10.5265. Min Act: -0.1700
Data Index: 650980 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6515. Min Range: -10.6515
Max Act: 10.4015. Min Act: -0.1700
Data Index: 7213405 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6515. Min Range: -10.6515
Max Act: 10.2765. Min Act: -0.1700
Data Index: 5416396 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6515. Min Range: -10.6515
Max Act: 10.0890. Min Act: -0.1700
Data Index: 4347353 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6515. Min Range: -10.6515
Max Act: 9.9640. Min Act: -0.1700
Data Index: 947426 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6515. Min Range: -10.6515
Max Act: 9.9640. Min Act: -0.1700
Data Index: 785500 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6515. Min Range: -10.6515
Max Act: 9.9015. Min Act: -0.1700
Data Index: 4185342 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6515. Min Range: -10.6515
Max Act: 9.8390. Min Act: -0.1700
Data Index: 1618267 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6515. Min Range: -10.6515
Max Act: 9.7765. Min Act: -0.1700
Data Index: 2859139 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6515. Min Range: -10.6515
Max Act: 9.7765. Min Act: -0.1700
Data Index: 6705743 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6515. Min Range: -10.6515
Max Act: 9.7140. Min Act: -0.1700
Data Index: 4681428 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6515. Min Range: -10.6515
Max Act: 9.7765. Min Act: -0.1700
Data Index: 3363574 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6515. Min Range: -10.6515
Max Act: 9.7140. Min Act: -0.1700
Data Index: 8193552 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6515. Min Range: -10.6515
Max Act: 9.6515. Min Act: -0.1700
Data Index: 3047399 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6515. Min Range: -10.6515
Max Act: 9.5890. Min Act: -0.1700
Data Index: 2626881 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6515. Min Range: -10.6515
Max Act: 9.6515. Min Act: -0.1700
Data Index: 8180306 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6515. Min Range: -10.6515
Max Act: 9.6515. Min Act: -0.1700
Data Index: 5547565 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6515. Min Range: -10.6515
Max Act: 9.6515. Min Act: -0.1700
Data Index: 5009767 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19