Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3144 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4333. Min Range: -8.4333
Max Act: 8.4333. Min Act: -0.1700
Data Index: 1635897 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4333. Min Range: -8.4333
Max Act: 8.2145. Min Act: -0.1700
Data Index: 4772855 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4333. Min Range: -8.4333
Max Act: 8.1833. Min Act: -0.1700
Data Index: 8107943 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4333. Min Range: -8.4333
Max Act: 7.9958. Min Act: -0.1700
Data Index: 6862168 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4333. Min Range: -8.4333
Max Act: 7.9958. Min Act: -0.1700
Data Index: 1119053 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4333. Min Range: -8.4333
Max Act: 7.9645. Min Act: -0.1700
Data Index: 3076902 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4333. Min Range: -8.4333
Max Act: 7.9333. Min Act: -0.1700
Data Index: 2389051 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4333. Min Range: -8.4333
Max Act: 7.9333. Min Act: -0.1700
Data Index: 6329587 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4333. Min Range: -8.4333
Max Act: 7.9333. Min Act: -0.1700
Data Index: 2281137 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4333. Min Range: -8.4333
Max Act: 7.7458. Min Act: -0.1700
Data Index: 5094958 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4333. Min Range: -8.4333
Max Act: 7.7770. Min Act: -0.1700
Data Index: 773768 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4333. Min Range: -8.4333
Max Act: 7.7145. Min Act: -0.1700
Data Index: 6019378 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4333. Min Range: -8.4333
Max Act: 7.7458. Min Act: -0.1700
Data Index: 7615830 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4333. Min Range: -8.4333
Max Act: 7.7145. Min Act: -0.1700
Data Index: 8570710 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4333. Min Range: -8.4333
Max Act: 7.7145. Min Act: -0.1700
Data Index: 4768473 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4333. Min Range: -8.4333
Max Act: 7.7145. Min Act: -0.1700
Data Index: 3715627 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4333. Min Range: -8.4333
Max Act: 7.6520. Min Act: -0.1700
Data Index: 4231316 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4333. Min Range: -8.4333
Max Act: 7.6833. Min Act: -0.1700
Data Index: 8500773 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4333. Min Range: -8.4333
Max Act: 7.6520. Min Act: -0.1700
Data Index: 5659679 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4333. Min Range: -8.4333
Max Act: 7.6208. Min Act: -0.1700
Data Index: 368986 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #19