Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2359 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2748. Min Range: -10.2748
Max Act: 10.2748. Min Act: -0.1700
Data Index: 2975736 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2748. Min Range: -10.2748
Max Act: 10.2748. Min Act: -0.1700
Data Index: 7446424 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2748. Min Range: -10.2748
Max Act: 10.2748. Min Act: -0.1700
Data Index: 218413 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2748. Min Range: -10.2748
Max Act: 10.2123. Min Act: -0.1700
Data Index: 4787898 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2748. Min Range: -10.2748
Max Act: 10.2123. Min Act: -0.1700
Data Index: 6392604 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2748. Min Range: -10.2748
Max Act: 10.2123. Min Act: -0.1700
Data Index: 5087076 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2748. Min Range: -10.2748
Max Act: 10.1498. Min Act: -0.1700
Data Index: 4849022 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2748. Min Range: -10.2748
Max Act: 10.1498. Min Act: -0.1700
Data Index: 5628059 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2748. Min Range: -10.2748
Max Act: 10.1498. Min Act: -0.1700
Data Index: 2852538 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2748. Min Range: -10.2748
Max Act: 10.0873. Min Act: -0.1700
Data Index: 579088 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2748. Min Range: -10.2748
Max Act: 10.0248. Min Act: -0.1700
Data Index: 180914 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2748. Min Range: -10.2748
Max Act: 10.0873. Min Act: -0.1700
Data Index: 6633448 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2748. Min Range: -10.2748
Max Act: 10.0873. Min Act: -0.1700
Data Index: 2816639 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2748. Min Range: -10.2748
Max Act: 10.0248. Min Act: -0.1700
Data Index: 5125287 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2748. Min Range: -10.2748
Max Act: 10.0873. Min Act: -0.1700
Data Index: 2465191 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2748. Min Range: -10.2748
Max Act: 10.0248. Min Act: -0.1700
Data Index: 2930005 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2748. Min Range: -10.2748
Max Act: 9.9623. Min Act: -0.1700
Data Index: 1879093 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2748. Min Range: -10.2748
Max Act: 10.0248. Min Act: -0.1700
Data Index: 8106132 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2748. Min Range: -10.2748
Max Act: 9.9623. Min Act: -0.1700
Data Index: 732039 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2748. Min Range: -10.2748
Max Act: 10.0248. Min Act: -0.1700
Data Index: 6230124 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #19