Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3962 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5800. Min Range: -6.5800
Max Act: 6.5800. Min Act: -0.1700
Data Index: 282231 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5800. Min Range: -6.5800
Max Act: 6.4237. Min Act: -0.1700
Data Index: 8725105 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5800. Min Range: -6.5800
Max Act: 6.3300. Min Act: -0.1700
Data Index: 414713 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5800. Min Range: -6.5800
Max Act: 6.2987. Min Act: -0.1700
Data Index: 2279102 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5800. Min Range: -6.5800
Max Act: 6.2675. Min Act: -0.1700
Data Index: 691077 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5800. Min Range: -6.5800
Max Act: 6.2362. Min Act: -0.1700
Data Index: 459399 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5800. Min Range: -6.5800
Max Act: 6.2362. Min Act: -0.1700
Data Index: 136087 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5800. Min Range: -6.5800
Max Act: 6.2362. Min Act: -0.1700
Data Index: 183321 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5800. Min Range: -6.5800
Max Act: 6.2362. Min Act: -0.1700
Data Index: 4574909 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5800. Min Range: -6.5800
Max Act: 6.1737. Min Act: -0.1700
Data Index: 767609 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5800. Min Range: -6.5800
Max Act: 6.1737. Min Act: -0.1700
Data Index: 4637732 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5800. Min Range: -6.5800
Max Act: 6.1737. Min Act: -0.1700
Data Index: 7998626 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5800. Min Range: -6.5800
Max Act: 6.1737. Min Act: -0.1700
Data Index: 183324 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5800. Min Range: -6.5800
Max Act: 6.1425. Min Act: -0.1700
Data Index: 5673681 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5800. Min Range: -6.5800
Max Act: 6.1737. Min Act: -0.1700
Data Index: 183325 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5800. Min Range: -6.5800
Max Act: 6.1425. Min Act: -0.1700
Data Index: 6454360 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5800. Min Range: -6.5800
Max Act: 6.1425. Min Act: -0.1700
Data Index: 4522513 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5800. Min Range: -6.5800
Max Act: 6.1425. Min Act: -0.1700
Data Index: 7447643 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5800. Min Range: -6.5800
Max Act: 6.0800. Min Act: -0.1700
Data Index: 6574557 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5800. Min Range: -6.5800
Max Act: 6.0800. Min Act: -0.1700
Data Index: 7128950 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #19