Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1373 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6590. Min Range: -3.6590
Max Act: 3.6590. Min Act: -0.1700
Data Index: 8214076 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6590. Min Range: -3.6590
Max Act: 3.5964. Min Act: -0.1700
Data Index: 4488639 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6590. Min Range: -3.6590
Max Act: 3.5964. Min Act: -0.1700
Data Index: 5509709 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6590. Min Range: -3.6590
Max Act: 3.5964. Min Act: -0.1700
Data Index: 4206650 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6590. Min Range: -3.6590
Max Act: 3.5964. Min Act: -0.1700
Data Index: 1136676 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6590. Min Range: -3.6590
Max Act: 3.5651. Min Act: -0.1700
Data Index: 5383994 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6590. Min Range: -3.6590
Max Act: 3.5651. Min Act: -0.1700
Data Index: 4953752 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6590. Min Range: -3.6590
Max Act: 3.5338. Min Act: -0.1700
Data Index: 2491431 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6590. Min Range: -3.6590
Max Act: 3.5338. Min Act: -0.1700
Data Index: 6269837 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6590. Min Range: -3.6590
Max Act: 3.5338. Min Act: -0.1700
Data Index: 8407160 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6590. Min Range: -3.6590
Max Act: 3.5338. Min Act: -0.1700
Data Index: 2853883 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6590. Min Range: -3.6590
Max Act: 3.5338. Min Act: -0.1700
Data Index: 4550392 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6590. Min Range: -3.6590
Max Act: 3.5338. Min Act: -0.1700
Data Index: 8482878 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6590. Min Range: -3.6590
Max Act: 3.5338. Min Act: -0.1700
Data Index: 660042 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6590. Min Range: -3.6590
Max Act: 3.5024. Min Act: -0.1700
Data Index: 554336 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6590. Min Range: -3.6590
Max Act: 3.5024. Min Act: -0.1700
Data Index: 7189686 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6590. Min Range: -3.6590
Max Act: 3.5024. Min Act: -0.1700
Data Index: 2433029 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6590. Min Range: -3.6590
Max Act: 3.5024. Min Act: -0.1700
Data Index: 5893232 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6590. Min Range: -3.6590
Max Act: 3.5024. Min Act: -0.1700
Data Index: 5456176 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6590. Min Range: -3.6590
Max Act: 3.5024. Min Act: -0.1700
Data Index: 5342597 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19