Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5093 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7929. Min Range: -8.7929
Max Act: 8.7929. Min Act: -0.1700
Data Index: 745872 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7929. Min Range: -8.7929
Max Act: 8.6679. Min Act: -0.1700
Data Index: 6517425 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7929. Min Range: -8.7929
Max Act: 8.6054. Min Act: -0.1700
Data Index: 4110207 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7929. Min Range: -8.7929
Max Act: 8.5429. Min Act: -0.1700
Data Index: 2859569 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7929. Min Range: -8.7929
Max Act: 8.5429. Min Act: -0.1700
Data Index: 8709688 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7929. Min Range: -8.7929
Max Act: 8.5429. Min Act: -0.1700
Data Index: 1712466 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7929. Min Range: -8.7929
Max Act: 8.4804. Min Act: -0.1700
Data Index: 5452024 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7929. Min Range: -8.7929
Max Act: 8.4804. Min Act: -0.1700
Data Index: 2214722 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7929. Min Range: -8.7929
Max Act: 8.3554. Min Act: -0.1700
Data Index: 690589 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7929. Min Range: -8.7929
Max Act: 8.3554. Min Act: -0.1700
Data Index: 4020384 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7929. Min Range: -8.7929
Max Act: 8.3554. Min Act: -0.1700
Data Index: 5452026 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7929. Min Range: -8.7929
Max Act: 8.2929. Min Act: -0.1700
Data Index: 8792286 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7929. Min Range: -8.7929
Max Act: 8.2929. Min Act: -0.1700
Data Index: 1140760 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7929. Min Range: -8.7929
Max Act: 8.2929. Min Act: -0.1700
Data Index: 821810 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7929. Min Range: -8.7929
Max Act: 8.2929. Min Act: -0.1700
Data Index: 8280324 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7929. Min Range: -8.7929
Max Act: 8.2929. Min Act: -0.1700
Data Index: 7451779 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7929. Min Range: -8.7929
Max Act: 8.2929. Min Act: -0.1700
Data Index: 1131539 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7929. Min Range: -8.7929
Max Act: 8.2304. Min Act: -0.1700
Data Index: 5559045 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7929. Min Range: -8.7929
Max Act: 8.2304. Min Act: -0.1700
Data Index: 2623432 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7929. Min Range: -8.7929
Max Act: 8.2304. Min Act: -0.1700
Data Index: 739109 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #19