Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 613 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3053. Min Range: -5.3053
Max Act: 5.3053. Min Act: -0.1700
Data Index: 4108444 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3053. Min Range: -5.3053
Max Act: 5.2741. Min Act: -0.1700
Data Index: 1607825 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3053. Min Range: -5.3053
Max Act: 5.2741. Min Act: -0.1700
Data Index: 6072848 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3053. Min Range: -5.3053
Max Act: 5.2116. Min Act: -0.1700
Data Index: 7588125 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3053. Min Range: -5.3053
Max Act: 5.1803. Min Act: -0.1700
Data Index: 3616284 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3053. Min Range: -5.3053
Max Act: 5.1491. Min Act: -0.1700
Data Index: 6072851 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3053. Min Range: -5.3053
Max Act: 5.0866. Min Act: -0.1700
Data Index: 3254112 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3053. Min Range: -5.3053
Max Act: 5.0866. Min Act: -0.1700
Data Index: 3442589 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3053. Min Range: -5.3053
Max Act: 5.0866. Min Act: -0.1700
Data Index: 1876735 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3053. Min Range: -5.3053
Max Act: 5.0553. Min Act: -0.1700
Data Index: 7416861 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3053. Min Range: -5.3053
Max Act: 5.0553. Min Act: -0.1700
Data Index: 4251536 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3053. Min Range: -5.3053
Max Act: 5.0553. Min Act: -0.1700
Data Index: 4871404 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3053. Min Range: -5.3053
Max Act: 5.0553. Min Act: -0.1700
Data Index: 5477366 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3053. Min Range: -5.3053
Max Act: 5.0553. Min Act: -0.1700
Data Index: 3163630 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3053. Min Range: -5.3053
Max Act: 5.0241. Min Act: -0.1700
Data Index: 262346 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3053. Min Range: -5.3053
Max Act: 5.0241. Min Act: -0.1700
Data Index: 1645130 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3053. Min Range: -5.3053
Max Act: 4.9616. Min Act: -0.1700
Data Index: 5964845 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3053. Min Range: -5.3053
Max Act: 5.0241. Min Act: -0.1700
Data Index: 4850743 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3053. Min Range: -5.3053
Max Act: 4.9928. Min Act: -0.1700
Data Index: 892049 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3053. Min Range: -5.3053
Max Act: 4.9928. Min Act: -0.1700
Data Index: 326432 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #19