Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2365 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.4762. Min Range: -2.4762
Max Act: 2.4762. Min Act: -0.1700
Data Index: 3788651 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4762. Min Range: -2.4762
Max Act: 2.3785. Min Act: -0.1700
Data Index: 6628576 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4762. Min Range: -2.4762
Max Act: 2.3785. Min Act: -0.1700
Data Index: 4055796 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4762. Min Range: -2.4762
Max Act: 2.3622. Min Act: -0.1700
Data Index: 4141911 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4762. Min Range: -2.4762
Max Act: 2.3458. Min Act: -0.1700
Data Index: 379645 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4762. Min Range: -2.4762
Max Act: 2.3458. Min Act: -0.1700
Data Index: 4929002 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4762. Min Range: -2.4762
Max Act: 2.3294. Min Act: -0.1700
Data Index: 1917943 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4762. Min Range: -2.4762
Max Act: 2.3294. Min Act: -0.1700
Data Index: 7778487 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4762. Min Range: -2.4762
Max Act: 2.3130. Min Act: -0.1700
Data Index: 65144 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4762. Min Range: -2.4762
Max Act: 2.3130. Min Act: -0.1700
Data Index: 4147493 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4762. Min Range: -2.4762
Max Act: 2.2965. Min Act: -0.1700
Data Index: 4820216 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4762. Min Range: -2.4762
Max Act: 2.2965. Min Act: -0.1700
Data Index: 1326508 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4762. Min Range: -2.4762
Max Act: 2.2965. Min Act: -0.1700
Data Index: 190696 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4762. Min Range: -2.4762
Max Act: 2.2800. Min Act: -0.1700
Data Index: 942220 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4762. Min Range: -2.4762
Max Act: 2.2800. Min Act: -0.1700
Data Index: 752902 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4762. Min Range: -2.4762
Max Act: 2.2800. Min Act: -0.1700
Data Index: 2828698 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4762. Min Range: -2.4762
Max Act: 2.2635. Min Act: -0.1700
Data Index: 2486600 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4762. Min Range: -2.4762
Max Act: 2.2800. Min Act: -0.1700
Data Index: 1024355 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4762. Min Range: -2.4762
Max Act: 2.2800. Min Act: -0.1700
Data Index: 407971 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4762. Min Range: -2.4762
Max Act: 2.2635. Min Act: -0.1700
Data Index: 5377179 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19