Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 259 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6828. Min Range: -2.6828
Max Act: 2.6828. Min Act: -0.1700
Data Index: 3889561 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6828. Min Range: -2.6828
Max Act: 2.6668. Min Act: -0.1700
Data Index: 815845 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6828. Min Range: -2.6828
Max Act: 2.6025. Min Act: -0.1700
Data Index: 6646978 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6828. Min Range: -2.6828
Max Act: 2.5864. Min Act: -0.1700
Data Index: 5585684 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6828. Min Range: -2.6828
Max Act: 2.5864. Min Act: -0.1700
Data Index: 4703817 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6828. Min Range: -2.6828
Max Act: 2.5703. Min Act: -0.1700
Data Index: 2122684 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6828. Min Range: -2.6828
Max Act: 2.5703. Min Act: -0.1700
Data Index: 3562100 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6828. Min Range: -2.6828
Max Act: 2.5703. Min Act: -0.1700
Data Index: 7668625 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6828. Min Range: -2.6828
Max Act: 2.5542. Min Act: -0.1700
Data Index: 7296375 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6828. Min Range: -2.6828
Max Act: 2.5703. Min Act: -0.1700
Data Index: 6700265 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6828. Min Range: -2.6828
Max Act: 2.5542. Min Act: -0.1700
Data Index: 5356929 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6828. Min Range: -2.6828
Max Act: 2.5380. Min Act: -0.1700
Data Index: 7076570 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6828. Min Range: -2.6828
Max Act: 2.5380. Min Act: -0.1700
Data Index: 4822591 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6828. Min Range: -2.6828
Max Act: 2.5380. Min Act: -0.1700
Data Index: 113640 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6828. Min Range: -2.6828
Max Act: 2.5380. Min Act: -0.1700
Data Index: 6917451 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6828. Min Range: -2.6828
Max Act: 2.5380. Min Act: -0.1700
Data Index: 6423156 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6828. Min Range: -2.6828
Max Act: 2.5380. Min Act: -0.1700
Data Index: 2353128 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6828. Min Range: -2.6828
Max Act: 2.5380. Min Act: -0.1700
Data Index: 5862750 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6828. Min Range: -2.6828
Max Act: 2.5219. Min Act: -0.1700
Data Index: 2138231 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6828. Min Range: -2.6828
Max Act: 2.5219. Min Act: -0.1700
Data Index: 7433096 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #19