Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3549 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2398. Min Range: -4.2398
Max Act: 4.2398. Min Act: -0.1700
Data Index: 3061162 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2398. Min Range: -4.2398
Max Act: 4.2398. Min Act: -0.1700
Data Index: 5511346 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2398. Min Range: -4.2398
Max Act: 4.2085. Min Act: -0.1700
Data Index: 3661652 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2398. Min Range: -4.2398
Max Act: 4.2085. Min Act: -0.1700
Data Index: 4063021 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2398. Min Range: -4.2398
Max Act: 4.2085. Min Act: -0.1700
Data Index: 4857246 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2398. Min Range: -4.2398
Max Act: 4.2085. Min Act: -0.1700
Data Index: 2007684 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2398. Min Range: -4.2398
Max Act: 4.2085. Min Act: -0.1700
Data Index: 8180729 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2398. Min Range: -4.2398
Max Act: 4.1773. Min Act: -0.1700
Data Index: 5939878 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2398. Min Range: -4.2398
Max Act: 4.1773. Min Act: -0.1700
Data Index: 5863529 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2398. Min Range: -4.2398
Max Act: 4.1773. Min Act: -0.1700
Data Index: 3397398 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2398. Min Range: -4.2398
Max Act: 4.1773. Min Act: -0.1700
Data Index: 8221124 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2398. Min Range: -4.2398
Max Act: 4.1773. Min Act: -0.1700
Data Index: 3056240 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2398. Min Range: -4.2398
Max Act: 4.1773. Min Act: -0.1700
Data Index: 2760257 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2398. Min Range: -4.2398
Max Act: 4.1460. Min Act: -0.1700
Data Index: 1051937 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2398. Min Range: -4.2398
Max Act: 4.1773. Min Act: -0.1700
Data Index: 5877859 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2398. Min Range: -4.2398
Max Act: 4.1773. Min Act: -0.1700
Data Index: 99731 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2398. Min Range: -4.2398
Max Act: 4.1773. Min Act: -0.1700
Data Index: 5614962 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2398. Min Range: -4.2398
Max Act: 4.1773. Min Act: -0.1700
Data Index: 5153452 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2398. Min Range: -4.2398
Max Act: 4.1773. Min Act: -0.1700
Data Index: 4474894 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2398. Min Range: -4.2398
Max Act: 4.1460. Min Act: -0.1700
Data Index: 522178 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19