Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4476 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5770. Min Range: -4.5770
Max Act: 4.5770. Min Act: -0.1700
Data Index: 1505880 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5770. Min Range: -4.5770
Max Act: 4.5458. Min Act: -0.1700
Data Index: 5962220 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5770. Min Range: -4.5770
Max Act: 4.4208. Min Act: -0.1700
Data Index: 5427457 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5770. Min Range: -4.5770
Max Act: 4.3895. Min Act: -0.1700
Data Index: 3426344 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5770. Min Range: -4.5770
Max Act: 4.3582. Min Act: -0.1700
Data Index: 1448700 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5770. Min Range: -4.5770
Max Act: 4.3582. Min Act: -0.1700
Data Index: 2163695 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5770. Min Range: -4.5770
Max Act: 4.3270. Min Act: -0.1700
Data Index: 260535 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5770. Min Range: -4.5770
Max Act: 4.2957. Min Act: -0.1700
Data Index: 8712672 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5770. Min Range: -4.5770
Max Act: 4.2645. Min Act: -0.1700
Data Index: 8657756 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5770. Min Range: -4.5770
Max Act: 4.2645. Min Act: -0.1700
Data Index: 5833703 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5770. Min Range: -4.5770
Max Act: 4.2332. Min Act: -0.1700
Data Index: 6941294 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5770. Min Range: -4.5770
Max Act: 4.2645. Min Act: -0.1700
Data Index: 6514226 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5770. Min Range: -4.5770
Max Act: 4.2332. Min Act: -0.1700
Data Index: 8564696 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5770. Min Range: -4.5770
Max Act: 4.2020. Min Act: -0.1700
Data Index: 6560605 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5770. Min Range: -4.5770
Max Act: 4.2020. Min Act: -0.1700
Data Index: 5084965 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5770. Min Range: -4.5770
Max Act: 4.2020. Min Act: -0.1700
Data Index: 1633328 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5770. Min Range: -4.5770
Max Act: 4.2020. Min Act: -0.1700
Data Index: 6420626 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5770. Min Range: -4.5770
Max Act: 4.1707. Min Act: -0.1700
Data Index: 1912562 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5770. Min Range: -4.5770
Max Act: 4.2020. Min Act: -0.1700
Data Index: 6736018 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5770. Min Range: -4.5770
Max Act: 4.2020. Min Act: -0.1700
Data Index: 1248230 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #19