Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3837 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5974. Min Range: -3.5974
Max Act: 3.5974. Min Act: -0.1700
Data Index: 3461632 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5974. Min Range: -3.5974
Max Act: 3.5035. Min Act: -0.1700
Data Index: 6272070 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5974. Min Range: -3.5974
Max Act: 3.4565. Min Act: -0.1700
Data Index: 5885847 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5974. Min Range: -3.5974
Max Act: 3.4721. Min Act: -0.1700
Data Index: 3461627 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5974. Min Range: -3.5974
Max Act: 3.4251. Min Act: -0.1700
Data Index: 1778447 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5974. Min Range: -3.5974
Max Act: 3.4408. Min Act: -0.1700
Data Index: 3583256 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5974. Min Range: -3.5974
Max Act: 3.4408. Min Act: -0.1700
Data Index: 1048916 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5974. Min Range: -3.5974
Max Act: 3.4251. Min Act: -0.1700
Data Index: 5738550 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5974. Min Range: -3.5974
Max Act: 3.4094. Min Act: -0.1700
Data Index: 964165 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5974. Min Range: -3.5974
Max Act: 3.4094. Min Act: -0.1700
Data Index: 7145976 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5974. Min Range: -3.5974
Max Act: 3.3938. Min Act: -0.1700
Data Index: 3416417 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5974. Min Range: -3.5974
Max Act: 3.3938. Min Act: -0.1700
Data Index: 8710591 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5974. Min Range: -3.5974
Max Act: 3.3938. Min Act: -0.1700
Data Index: 6500677 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5974. Min Range: -3.5974
Max Act: 3.3938. Min Act: -0.1700
Data Index: 3566295 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5974. Min Range: -3.5974
Max Act: 3.3781. Min Act: -0.1700
Data Index: 3040094 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5974. Min Range: -3.5974
Max Act: 3.3624. Min Act: -0.1700
Data Index: 6695496 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5974. Min Range: -3.5974
Max Act: 3.3781. Min Act: -0.1700
Data Index: 7350396 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5974. Min Range: -3.5974
Max Act: 3.3781. Min Act: -0.1700
Data Index: 3134097 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5974. Min Range: -3.5974
Max Act: 3.3624. Min Act: -0.1700
Data Index: 8812591 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5974. Min Range: -3.5974
Max Act: 3.3467. Min Act: -0.1700
Data Index: 3602758 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19