Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 704 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0574. Min Range: -4.0574
Max Act: 4.0574. Min Act: -0.1700
Data Index: 2107848 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0574. Min Range: -4.0574
Max Act: 4.0262. Min Act: -0.1700
Data Index: 1281222 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0574. Min Range: -4.0574
Max Act: 4.0262. Min Act: -0.1700
Data Index: 7058721 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0574. Min Range: -4.0574
Max Act: 3.9949. Min Act: -0.1700
Data Index: 3626673 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0574. Min Range: -4.0574
Max Act: 3.9949. Min Act: -0.1700
Data Index: 5885986 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0574. Min Range: -4.0574
Max Act: 3.9949. Min Act: -0.1700
Data Index: 687529 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0574. Min Range: -4.0574
Max Act: 3.9949. Min Act: -0.1700
Data Index: 5788410 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0574. Min Range: -4.0574
Max Act: 3.9949. Min Act: -0.1700
Data Index: 5077844 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0574. Min Range: -4.0574
Max Act: 3.9949. Min Act: -0.1700
Data Index: 8177982 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0574. Min Range: -4.0574
Max Act: 3.9949. Min Act: -0.1700
Data Index: 4361473 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0574. Min Range: -4.0574
Max Act: 3.9949. Min Act: -0.1700
Data Index: 7723161 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0574. Min Range: -4.0574
Max Act: 3.9949. Min Act: -0.1700
Data Index: 6498534 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0574. Min Range: -4.0574
Max Act: 3.9949. Min Act: -0.1700
Data Index: 1677827 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0574. Min Range: -4.0574
Max Act: 3.9949. Min Act: -0.1700
Data Index: 2942398 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0574. Min Range: -4.0574
Max Act: 3.9637. Min Act: -0.1700
Data Index: 5076334 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0574. Min Range: -4.0574
Max Act: 3.9949. Min Act: -0.1700
Data Index: 5606552 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0574. Min Range: -4.0574
Max Act: 3.9324. Min Act: -0.1700
Data Index: 69600 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0574. Min Range: -4.0574
Max Act: 3.9637. Min Act: -0.1700
Data Index: 5989728 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0574. Min Range: -4.0574
Max Act: 3.9637. Min Act: -0.1700
Data Index: 6237420 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0574. Min Range: -4.0574
Max Act: 3.9637. Min Act: -0.1700
Data Index: 6287553 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #19