Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1697 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0850. Min Range: -4.0850
Max Act: 4.0850. Min Act: -0.1700
Data Index: 8544243 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0850. Min Range: -4.0850
Max Act: 4.0537. Min Act: -0.1700
Data Index: 5045451 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0850. Min Range: -4.0850
Max Act: 3.9599. Min Act: -0.1700
Data Index: 4656164 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0850. Min Range: -4.0850
Max Act: 3.9131. Min Act: -0.1700
Data Index: 8809942 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0850. Min Range: -4.0850
Max Act: 3.8662. Min Act: -0.1700
Data Index: 6248224 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0850. Min Range: -4.0850
Max Act: 3.8349. Min Act: -0.1700
Data Index: 1481695 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0850. Min Range: -4.0850
Max Act: 3.8192. Min Act: -0.1700
Data Index: 6299361 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0850. Min Range: -4.0850
Max Act: 3.8505. Min Act: -0.1700
Data Index: 4883807 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0850. Min Range: -4.0850
Max Act: 3.8036. Min Act: -0.1700
Data Index: 2721630 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0850. Min Range: -4.0850
Max Act: 3.8036. Min Act: -0.1700
Data Index: 48930 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0850. Min Range: -4.0850
Max Act: 3.8036. Min Act: -0.1700
Data Index: 4276938 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0850. Min Range: -4.0850
Max Act: 3.7880. Min Act: -0.1700
Data Index: 8113544 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0850. Min Range: -4.0850
Max Act: 3.7723. Min Act: -0.1700
Data Index: 2763493 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0850. Min Range: -4.0850
Max Act: 3.7880. Min Act: -0.1700
Data Index: 3281181 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0850. Min Range: -4.0850
Max Act: 3.7567. Min Act: -0.1700
Data Index: 3566121 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0850. Min Range: -4.0850
Max Act: 3.7567. Min Act: -0.1700
Data Index: 1772356 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0850. Min Range: -4.0850
Max Act: 3.7567. Min Act: -0.1700
Data Index: 169679 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0850. Min Range: -4.0850
Max Act: 3.7567. Min Act: -0.1700
Data Index: 1546742 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0850. Min Range: -4.0850
Max Act: 3.7567. Min Act: -0.1700
Data Index: 3637342 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0850. Min Range: -4.0850
Max Act: 3.7567. Min Act: -0.1700
Data Index: 1238646 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #19