Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6302 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7530. Min Range: -6.7530
Max Act: 6.7530. Min Act: -0.1700
Data Index: 7113343 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7530. Min Range: -6.7530
Max Act: 6.6905. Min Act: -0.1700
Data Index: 630286 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7530. Min Range: -6.7530
Max Act: 6.6592. Min Act: -0.1700
Data Index: 5665302 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7530. Min Range: -6.7530
Max Act: 6.5967. Min Act: -0.1700
Data Index: 5234978 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7530. Min Range: -6.7530
Max Act: 6.5655. Min Act: -0.1700
Data Index: 2281252 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7530. Min Range: -6.7530
Max Act: 6.5655. Min Act: -0.1700
Data Index: 6488578 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7530. Min Range: -6.7530
Max Act: 6.5655. Min Act: -0.1700
Data Index: 2620488 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7530. Min Range: -6.7530
Max Act: 6.4405. Min Act: -0.1700
Data Index: 5964412 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7530. Min Range: -6.7530
Max Act: 6.4405. Min Act: -0.1700
Data Index: 5964352 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7530. Min Range: -6.7530
Max Act: 6.4092. Min Act: -0.1700
Data Index: 2757783 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7530. Min Range: -6.7530
Max Act: 6.4092. Min Act: -0.1700
Data Index: 4080686 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7530. Min Range: -6.7530
Max Act: 6.4092. Min Act: -0.1700
Data Index: 5850136 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7530. Min Range: -6.7530
Max Act: 6.3780. Min Act: -0.1700
Data Index: 2620973 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7530. Min Range: -6.7530
Max Act: 6.3780. Min Act: -0.1700
Data Index: 2644261 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7530. Min Range: -6.7530
Max Act: 6.3780. Min Act: -0.1700
Data Index: 7425278 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7530. Min Range: -6.7530
Max Act: 6.3780. Min Act: -0.1700
Data Index: 7335444 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7530. Min Range: -6.7530
Max Act: 6.3780. Min Act: -0.1700
Data Index: 1083118 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7530. Min Range: -6.7530
Max Act: 6.3467. Min Act: -0.1700
Data Index: 7111783 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7530. Min Range: -6.7530
Max Act: 6.3467. Min Act: -0.1700
Data Index: 5204131 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7530. Min Range: -6.7530
Max Act: 6.3155. Min Act: -0.1700
Data Index: 5736716 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #19