Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 23 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6460. Min Range: -4.6460
Max Act: 4.6460. Min Act: -0.1700
Data Index: 2111053 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6460. Min Range: -4.6460
Max Act: 4.6460. Min Act: -0.1700
Data Index: 7828291 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6460. Min Range: -4.6460
Max Act: 4.5835. Min Act: -0.1700
Data Index: 7841167 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6460. Min Range: -4.6460
Max Act: 4.5523. Min Act: -0.1700
Data Index: 2137449 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6460. Min Range: -4.6460
Max Act: 4.4898. Min Act: -0.1700
Data Index: 6407956 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6460. Min Range: -4.6460
Max Act: 4.4898. Min Act: -0.1700
Data Index: 783064 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6460. Min Range: -4.6460
Max Act: 4.4585. Min Act: -0.1700
Data Index: 7649970 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6460. Min Range: -4.6460
Max Act: 4.4585. Min Act: -0.1700
Data Index: 8609672 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6460. Min Range: -4.6460
Max Act: 4.4273. Min Act: -0.1700
Data Index: 7915991 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6460. Min Range: -4.6460
Max Act: 4.3960. Min Act: -0.1700
Data Index: 902546 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6460. Min Range: -4.6460
Max Act: 4.3648. Min Act: -0.1700
Data Index: 2924404 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6460. Min Range: -4.6460
Max Act: 4.3023. Min Act: -0.1700
Data Index: 2694790 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6460. Min Range: -4.6460
Max Act: 4.3023. Min Act: -0.1700
Data Index: 3386883 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6460. Min Range: -4.6460
Max Act: 4.3023. Min Act: -0.1700
Data Index: 2234643 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6460. Min Range: -4.6460
Max Act: 4.3023. Min Act: -0.1700
Data Index: 3801939 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6460. Min Range: -4.6460
Max Act: 4.2710. Min Act: -0.1700
Data Index: 1068996 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6460. Min Range: -4.6460
Max Act: 4.2710. Min Act: -0.1700
Data Index: 448846 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6460. Min Range: -4.6460
Max Act: 4.2710. Min Act: -0.1700
Data Index: 6964305 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6460. Min Range: -4.6460
Max Act: 4.2398. Min Act: -0.1700
Data Index: 3797074 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6460. Min Range: -4.6460
Max Act: 4.2398. Min Act: -0.1700
Data Index: 3360907 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19