Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2336 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5895. Min Range: -6.5895
Max Act: 6.5895. Min Act: -0.1700
Data Index: 8147974 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5895. Min Range: -6.5895
Max Act: 6.3083. Min Act: -0.1700
Data Index: 68619 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5895. Min Range: -6.5895
Max Act: 6.3395. Min Act: -0.1700
Data Index: 3267388 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5895. Min Range: -6.5895
Max Act: 6.2770. Min Act: -0.1700
Data Index: 1984404 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5895. Min Range: -6.5895
Max Act: 6.2458. Min Act: -0.1700
Data Index: 3530096 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5895. Min Range: -6.5895
Max Act: 6.2145. Min Act: -0.1700
Data Index: 2410014 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5895. Min Range: -6.5895
Max Act: 6.2145. Min Act: -0.1700
Data Index: 2977854 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5895. Min Range: -6.5895
Max Act: 6.1833. Min Act: -0.1700
Data Index: 6008454 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5895. Min Range: -6.5895
Max Act: 6.1833. Min Act: -0.1700
Data Index: 5771530 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5895. Min Range: -6.5895
Max Act: 6.1833. Min Act: -0.1700
Data Index: 1421078 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5895. Min Range: -6.5895
Max Act: 6.1520. Min Act: -0.1700
Data Index: 7181058 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5895. Min Range: -6.5895
Max Act: 6.1208. Min Act: -0.1700
Data Index: 572615 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5895. Min Range: -6.5895
Max Act: 6.1208. Min Act: -0.1700
Data Index: 4125588 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5895. Min Range: -6.5895
Max Act: 6.0583. Min Act: -0.1700
Data Index: 5787405 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5895. Min Range: -6.5895
Max Act: 6.0583. Min Act: -0.1700
Data Index: 6576833 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5895. Min Range: -6.5895
Max Act: 6.1208. Min Act: -0.1700
Data Index: 199236 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5895. Min Range: -6.5895
Max Act: 6.0583. Min Act: -0.1700
Data Index: 4072603 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5895. Min Range: -6.5895
Max Act: 6.0583. Min Act: -0.1700
Data Index: 5153579 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5895. Min Range: -6.5895
Max Act: 6.0583. Min Act: -0.1700
Data Index: 1600064 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5895. Min Range: -6.5895
Max Act: 6.0583. Min Act: -0.1700
Data Index: 6045275 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #19