Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 456 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2756. Min Range: -4.2756
Max Act: 4.2756. Min Act: -0.1700
Data Index: 2703269 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2756. Min Range: -4.2756
Max Act: 4.2756. Min Act: -0.1700
Data Index: 1727787 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2756. Min Range: -4.2756
Max Act: 4.2444. Min Act: -0.1700
Data Index: 6711136 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2756. Min Range: -4.2756
Max Act: 4.2444. Min Act: -0.1700
Data Index: 4629166 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2756. Min Range: -4.2756
Max Act: 4.2444. Min Act: -0.1700
Data Index: 7480443 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2756. Min Range: -4.2756
Max Act: 4.2131. Min Act: -0.1700
Data Index: 6441291 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2756. Min Range: -4.2756
Max Act: 4.1819. Min Act: -0.1700
Data Index: 4773414 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2756. Min Range: -4.2756
Max Act: 4.1819. Min Act: -0.1700
Data Index: 4742124 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2756. Min Range: -4.2756
Max Act: 4.2131. Min Act: -0.1700
Data Index: 2395314 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2756. Min Range: -4.2756
Max Act: 4.2131. Min Act: -0.1700
Data Index: 7562701 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2756. Min Range: -4.2756
Max Act: 4.2131. Min Act: -0.1700
Data Index: 7310783 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2756. Min Range: -4.2756
Max Act: 4.2131. Min Act: -0.1700
Data Index: 1901770 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2756. Min Range: -4.2756
Max Act: 4.2131. Min Act: -0.1700
Data Index: 6655397 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2756. Min Range: -4.2756
Max Act: 4.2131. Min Act: -0.1700
Data Index: 6043846 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2756. Min Range: -4.2756
Max Act: 4.1819. Min Act: -0.1700
Data Index: 1707145 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2756. Min Range: -4.2756
Max Act: 4.1819. Min Act: -0.1700
Data Index: 3799206 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2756. Min Range: -4.2756
Max Act: 4.1819. Min Act: -0.1700
Data Index: 4109299 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2756. Min Range: -4.2756
Max Act: 4.1819. Min Act: -0.1700
Data Index: 2323859 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2756. Min Range: -4.2756
Max Act: 4.1819. Min Act: -0.1700
Data Index: 4138719 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2756. Min Range: -4.2756
Max Act: 4.1819. Min Act: -0.1700
Data Index: 4184540 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19