Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3552 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3759. Min Range: -4.3759
Max Act: 4.3759. Min Act: -0.1700
Data Index: 6215576 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3759. Min Range: -4.3759
Max Act: 4.1572. Min Act: -0.1700
Data Index: 5802750 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3759. Min Range: -4.3759
Max Act: 4.1572. Min Act: -0.1700
Data Index: 4377473 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3759. Min Range: -4.3759
Max Act: 4.1259. Min Act: -0.1700
Data Index: 5946228 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3759. Min Range: -4.3759
Max Act: 4.0947. Min Act: -0.1700
Data Index: 2045114 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3759. Min Range: -4.3759
Max Act: 4.0634. Min Act: -0.1700
Data Index: 2268659 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3759. Min Range: -4.3759
Max Act: 4.0634. Min Act: -0.1700
Data Index: 511416 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3759. Min Range: -4.3759
Max Act: 4.0634. Min Act: -0.1700
Data Index: 3903791 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3759. Min Range: -4.3759
Max Act: 4.0321. Min Act: -0.1700
Data Index: 5898340 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3759. Min Range: -4.3759
Max Act: 4.0009. Min Act: -0.1700
Data Index: 756692 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3759. Min Range: -4.3759
Max Act: 4.0009. Min Act: -0.1700
Data Index: 1011517 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3759. Min Range: -4.3759
Max Act: 4.0009. Min Act: -0.1700
Data Index: 4029083 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3759. Min Range: -4.3759
Max Act: 4.0009. Min Act: -0.1700
Data Index: 2125127 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3759. Min Range: -4.3759
Max Act: 3.9696. Min Act: -0.1700
Data Index: 8531098 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3759. Min Range: -4.3759
Max Act: 3.9696. Min Act: -0.1700
Data Index: 1011511 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3759. Min Range: -4.3759
Max Act: 4.0009. Min Act: -0.1700
Data Index: 7629676 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3759. Min Range: -4.3759
Max Act: 3.9696. Min Act: -0.1700
Data Index: 934234 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3759. Min Range: -4.3759
Max Act: 3.9384. Min Act: -0.1700
Data Index: 4064222 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3759. Min Range: -4.3759
Max Act: 3.9071. Min Act: -0.1700
Data Index: 1828744 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3759. Min Range: -4.3759
Max Act: 3.9384. Min Act: -0.1700
Data Index: 7052515 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #19