Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2407 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5488. Min Range: -4.5488
Max Act: 4.5488. Min Act: -0.1700
Data Index: 685372 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5488. Min Range: -4.5488
Max Act: 4.2050. Min Act: -0.1699
Data Index: 6036658 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5488. Min Range: -4.5488
Max Act: 4.1113. Min Act: -0.1700
Data Index: 7282221 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5488. Min Range: -4.5488
Max Act: 4.1113. Min Act: -0.1700
Data Index: 1920940 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5488. Min Range: -4.5488
Max Act: 4.0800. Min Act: -0.1700
Data Index: 908848 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5488. Min Range: -4.5488
Max Act: 4.0800. Min Act: -0.1700
Data Index: 2929507 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5488. Min Range: -4.5488
Max Act: 4.0800. Min Act: -0.1700
Data Index: 3484818 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5488. Min Range: -4.5488
Max Act: 4.0487. Min Act: -0.1700
Data Index: 8563025 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5488. Min Range: -4.5488
Max Act: 4.0175. Min Act: -0.1700
Data Index: 2330357 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5488. Min Range: -4.5488
Max Act: 3.9862. Min Act: -0.1700
Data Index: 421036 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5488. Min Range: -4.5488
Max Act: 3.9862. Min Act: -0.1700
Data Index: 7175617 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5488. Min Range: -4.5488
Max Act: 3.9862. Min Act: -0.1700
Data Index: 6835863 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5488. Min Range: -4.5488
Max Act: 3.9550. Min Act: -0.1700
Data Index: 324592 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5488. Min Range: -4.5488
Max Act: 3.9550. Min Act: -0.1700
Data Index: 8517776 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5488. Min Range: -4.5488
Max Act: 3.9862. Min Act: -0.1700
Data Index: 1805722 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5488. Min Range: -4.5488
Max Act: 3.9550. Min Act: -0.1700
Data Index: 8140363 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5488. Min Range: -4.5488
Max Act: 3.8924. Min Act: -0.1700
Data Index: 1547772 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5488. Min Range: -4.5488
Max Act: 3.9237. Min Act: -0.1700
Data Index: 3627857 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5488. Min Range: -4.5488
Max Act: 3.9237. Min Act: -0.1700
Data Index: 6367158 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5488. Min Range: -4.5488
Max Act: 3.9237. Min Act: -0.1700
Data Index: 3916241 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #19