Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3203 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2019. Min Range: -6.2019
Max Act: 6.2019. Min Act: -0.1700
Data Index: 1920146 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2019. Min Range: -6.2019
Max Act: 6.2019. Min Act: -0.1700
Data Index: 117670 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2019. Min Range: -6.2019
Max Act: 6.2019. Min Act: -0.1700
Data Index: 2126982 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2019. Min Range: -6.2019
Max Act: 6.1394. Min Act: -0.1700
Data Index: 4004780 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2019. Min Range: -6.2019
Max Act: 6.1081. Min Act: -0.1700
Data Index: 2898088 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2019. Min Range: -6.2019
Max Act: 6.0769. Min Act: -0.1700
Data Index: 2254369 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2019. Min Range: -6.2019
Max Act: 6.0144. Min Act: -0.1700
Data Index: 2974413 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2019. Min Range: -6.2019
Max Act: 5.9831. Min Act: -0.1700
Data Index: 8410081 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2019. Min Range: -6.2019
Max Act: 5.9831. Min Act: -0.1700
Data Index: 8325022 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2019. Min Range: -6.2019
Max Act: 5.9519. Min Act: -0.1700
Data Index: 1229857 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2019. Min Range: -6.2019
Max Act: 5.9519. Min Act: -0.1700
Data Index: 34426 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2019. Min Range: -6.2019
Max Act: 5.9519. Min Act: -0.1700
Data Index: 8415108 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2019. Min Range: -6.2019
Max Act: 5.9206. Min Act: -0.1700
Data Index: 2530185 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2019. Min Range: -6.2019
Max Act: 5.9206. Min Act: -0.1700
Data Index: 53583 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2019. Min Range: -6.2019
Max Act: 5.8894. Min Act: -0.1700
Data Index: 2195709 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2019. Min Range: -6.2019
Max Act: 5.8894. Min Act: -0.1700
Data Index: 2397338 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2019. Min Range: -6.2019
Max Act: 5.8894. Min Act: -0.1700
Data Index: 8008168 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2019. Min Range: -6.2019
Max Act: 5.8894. Min Act: -0.1700
Data Index: 3647246 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2019. Min Range: -6.2019
Max Act: 5.8894. Min Act: -0.1700
Data Index: 4065660 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2019. Min Range: -6.2019
Max Act: 5.8894. Min Act: -0.1700
Data Index: 7650853 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #19