Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6002 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5795. Min Range: -6.5795
Max Act: 6.5795. Min Act: -0.1700
Data Index: 3816469 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5795. Min Range: -6.5795
Max Act: 6.3920. Min Act: -0.1700
Data Index: 7101915 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5795. Min Range: -6.5795
Max Act: 6.3295. Min Act: -0.1700
Data Index: 4590827 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5795. Min Range: -6.5795
Max Act: 6.2982. Min Act: -0.1700
Data Index: 734242 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5795. Min Range: -6.5795
Max Act: 6.2670. Min Act: -0.1700
Data Index: 7038720 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5795. Min Range: -6.5795
Max Act: 6.2670. Min Act: -0.1700
Data Index: 96993 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5795. Min Range: -6.5795
Max Act: 6.2670. Min Act: -0.1700
Data Index: 8363745 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5795. Min Range: -6.5795
Max Act: 6.2357. Min Act: -0.1700
Data Index: 8244273 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5795. Min Range: -6.5795
Max Act: 6.2357. Min Act: -0.1700
Data Index: 2052221 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5795. Min Range: -6.5795
Max Act: 6.2045. Min Act: -0.1700
Data Index: 2865082 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5795. Min Range: -6.5795
Max Act: 6.1732. Min Act: -0.1700
Data Index: 7883832 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5795. Min Range: -6.5795
Max Act: 6.1732. Min Act: -0.1700
Data Index: 1491621 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5795. Min Range: -6.5795
Max Act: 6.1420. Min Act: -0.1700
Data Index: 3002068 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5795. Min Range: -6.5795
Max Act: 6.1107. Min Act: -0.1700
Data Index: 3015012 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5795. Min Range: -6.5795
Max Act: 6.1107. Min Act: -0.1700
Data Index: 3472066 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5795. Min Range: -6.5795
Max Act: 6.1107. Min Act: -0.1700
Data Index: 7277796 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5795. Min Range: -6.5795
Max Act: 6.1107. Min Act: -0.1700
Data Index: 2459735 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5795. Min Range: -6.5795
Max Act: 6.0795. Min Act: -0.1700
Data Index: 8621070 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5795. Min Range: -6.5795
Max Act: 6.1107. Min Act: -0.1700
Data Index: 6433734 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5795. Min Range: -6.5795
Max Act: 6.0482. Min Act: -0.1700
Data Index: 7034818 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #19