Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4726 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2046. Min Range: -7.2046
Max Act: 7.2046. Min Act: -0.1700
Data Index: 5570018 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2046. Min Range: -7.2046
Max Act: 6.7671. Min Act: -0.1700
Data Index: 5159167 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2046. Min Range: -7.2046
Max Act: 6.6421. Min Act: -0.1700
Data Index: 7726709 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2046. Min Range: -7.2046
Max Act: 6.5796. Min Act: -0.1700
Data Index: 5724157 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2046. Min Range: -7.2046
Max Act: 6.5483. Min Act: -0.1700
Data Index: 2055573 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2046. Min Range: -7.2046
Max Act: 6.5483. Min Act: -0.1700
Data Index: 3185625 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2046. Min Range: -7.2046
Max Act: 6.5171. Min Act: -0.1700
Data Index: 6418322 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2046. Min Range: -7.2046
Max Act: 6.5171. Min Act: -0.1700
Data Index: 2751069 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2046. Min Range: -7.2046
Max Act: 6.4546. Min Act: -0.1700
Data Index: 7378010 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2046. Min Range: -7.2046
Max Act: 6.4233. Min Act: -0.1700
Data Index: 8415628 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2046. Min Range: -7.2046
Max Act: 6.4233. Min Act: -0.1700
Data Index: 5729324 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2046. Min Range: -7.2046
Max Act: 6.4233. Min Act: -0.1700
Data Index: 7792729 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2046. Min Range: -7.2046
Max Act: 6.3921. Min Act: -0.1700
Data Index: 7377456 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2046. Min Range: -7.2046
Max Act: 6.4233. Min Act: -0.1700
Data Index: 3834352 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2046. Min Range: -7.2046
Max Act: 6.3921. Min Act: -0.1700
Data Index: 6188366 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2046. Min Range: -7.2046
Max Act: 6.3921. Min Act: -0.1700
Data Index: 8226859 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2046. Min Range: -7.2046
Max Act: 6.3921. Min Act: -0.1700
Data Index: 6213031 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2046. Min Range: -7.2046
Max Act: 6.3921. Min Act: -0.1700
Data Index: 5544314 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2046. Min Range: -7.2046
Max Act: 6.3608. Min Act: -0.1700
Data Index: 1809840 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2046. Min Range: -7.2046
Max Act: 6.3608. Min Act: -0.1700
Data Index: 6399633 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19