Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4065 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6590. Min Range: -2.6590
Max Act: 2.6590. Min Act: -0.1700
Data Index: 3148191 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6590. Min Range: -2.6590
Max Act: 2.6590. Min Act: -0.1700
Data Index: 7027671 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6590. Min Range: -2.6590
Max Act: 2.6590. Min Act: -0.1700
Data Index: 3229797 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6590. Min Range: -2.6590
Max Act: 2.6430. Min Act: -0.1700
Data Index: 177288 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6590. Min Range: -2.6590
Max Act: 2.6269. Min Act: -0.1700
Data Index: 3136180 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6590. Min Range: -2.6590
Max Act: 2.6269. Min Act: -0.1700
Data Index: 3769613 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6590. Min Range: -2.6590
Max Act: 2.6269. Min Act: -0.1700
Data Index: 1012851 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6590. Min Range: -2.6590
Max Act: 2.6108. Min Act: -0.1700
Data Index: 3918315 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6590. Min Range: -2.6590
Max Act: 2.5947. Min Act: -0.1700
Data Index: 4168141 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6590. Min Range: -2.6590
Max Act: 2.5947. Min Act: -0.1700
Data Index: 4476183 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6590. Min Range: -2.6590
Max Act: 2.5947. Min Act: -0.1700
Data Index: 4877761 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6590. Min Range: -2.6590
Max Act: 2.5786. Min Act: -0.1700
Data Index: 476467 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6590. Min Range: -2.6590
Max Act: 2.5786. Min Act: -0.1700
Data Index: 2135786 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6590. Min Range: -2.6590
Max Act: 2.5625. Min Act: -0.1700
Data Index: 784110 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6590. Min Range: -2.6590
Max Act: 2.5786. Min Act: -0.1700
Data Index: 637713 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6590. Min Range: -2.6590
Max Act: 2.5786. Min Act: -0.1700
Data Index: 7839801 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6590. Min Range: -2.6590
Max Act: 2.5625. Min Act: -0.1700
Data Index: 159491 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6590. Min Range: -2.6590
Max Act: 2.5625. Min Act: -0.1700
Data Index: 7750501 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6590. Min Range: -2.6590
Max Act: 2.5464. Min Act: -0.1700
Data Index: 3761906 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6590. Min Range: -2.6590
Max Act: 2.5464. Min Act: -0.1700
Data Index: 4288558 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19