Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5115 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8706. Min Range: -2.8706
Max Act: 2.8706. Min Act: -0.1700
Data Index: 5050785 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8706. Min Range: -2.8706
Max Act: 2.8388. Min Act: -0.1700
Data Index: 3981900 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8706. Min Range: -2.8706
Max Act: 2.8229. Min Act: -0.1700
Data Index: 3636424 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8706. Min Range: -2.8706
Max Act: 2.8229. Min Act: -0.1700
Data Index: 8414910 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8706. Min Range: -2.8706
Max Act: 2.8229. Min Act: -0.1700
Data Index: 7392259 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8706. Min Range: -2.8706
Max Act: 2.8070. Min Act: -0.1700
Data Index: 4855827 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8706. Min Range: -2.8706
Max Act: 2.7911. Min Act: -0.1700
Data Index: 6031013 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8706. Min Range: -2.8706
Max Act: 2.8070. Min Act: -0.1700
Data Index: 8406729 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8706. Min Range: -2.8706
Max Act: 2.8070. Min Act: -0.1700
Data Index: 8550931 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8706. Min Range: -2.8706
Max Act: 2.8070. Min Act: -0.1700
Data Index: 5997663 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8706. Min Range: -2.8706
Max Act: 2.7911. Min Act: -0.1700
Data Index: 5206428 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8706. Min Range: -2.8706
Max Act: 2.7751. Min Act: -0.1700
Data Index: 2239246 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8706. Min Range: -2.8706
Max Act: 2.7751. Min Act: -0.1700
Data Index: 4164333 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8706. Min Range: -2.8706
Max Act: 2.7592. Min Act: -0.1700
Data Index: 348827 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8706. Min Range: -2.8706
Max Act: 2.7751. Min Act: -0.1700
Data Index: 4403037 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8706. Min Range: -2.8706
Max Act: 2.7592. Min Act: -0.1700
Data Index: 3933564 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8706. Min Range: -2.8706
Max Act: 2.7592. Min Act: -0.1700
Data Index: 4247157 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8706. Min Range: -2.8706
Max Act: 2.7592. Min Act: -0.1700
Data Index: 8417238 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8706. Min Range: -2.8706
Max Act: 2.7592. Min Act: -0.1700
Data Index: 2675437 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8706. Min Range: -2.8706
Max Act: 2.7432. Min Act: -0.1700
Data Index: 4697595 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #19