Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 12 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0215. Min Range: -9.0215
Max Act: 9.0215. Min Act: -0.1700
Data Index: 2710741 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0215. Min Range: -9.0215
Max Act: 8.8965. Min Act: -0.1700
Data Index: 1257351 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0215. Min Range: -9.0215
Max Act: 8.7090. Min Act: -0.1700
Data Index: 2783032 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0215. Min Range: -9.0215
Max Act: 8.6465. Min Act: -0.1700
Data Index: 8627954 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0215. Min Range: -9.0215
Max Act: 8.6465. Min Act: -0.1700
Data Index: 5125011 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0215. Min Range: -9.0215
Max Act: 8.5840. Min Act: -0.1700
Data Index: 5902229 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0215. Min Range: -9.0215
Max Act: 8.5840. Min Act: -0.1700
Data Index: 7510246 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0215. Min Range: -9.0215
Max Act: 8.4590. Min Act: -0.1700
Data Index: 6720345 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0215. Min Range: -9.0215
Max Act: 8.3965. Min Act: -0.1700
Data Index: 26136 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0215. Min Range: -9.0215
Max Act: 8.3340. Min Act: -0.1700
Data Index: 8168747 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0215. Min Range: -9.0215
Max Act: 8.3340. Min Act: -0.1700
Data Index: 5962719 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0215. Min Range: -9.0215
Max Act: 8.2090. Min Act: -0.1700
Data Index: 5453803 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0215. Min Range: -9.0215
Max Act: 8.2090. Min Act: -0.1700
Data Index: 851257 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0215. Min Range: -9.0215
Max Act: 8.2090. Min Act: -0.1700
Data Index: 8320130 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0215. Min Range: -9.0215
Max Act: 8.0840. Min Act: -0.1700
Data Index: 6247034 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0215. Min Range: -9.0215
Max Act: 8.1465. Min Act: -0.1700
Data Index: 8615900 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0215. Min Range: -9.0215
Max Act: 8.1465. Min Act: -0.1700
Data Index: 4342818 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0215. Min Range: -9.0215
Max Act: 8.0840. Min Act: -0.1700
Data Index: 4317721 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0215. Min Range: -9.0215
Max Act: 8.0840. Min Act: -0.1700
Data Index: 7168555 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0215. Min Range: -9.0215
Max Act: 8.0215. Min Act: -0.1700
Data Index: 8294007 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #19