Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5858 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9720. Min Range: -6.9720
Max Act: 6.9720. Min Act: -0.1700
Data Index: 8097376 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9720. Min Range: -6.9720
Max Act: 6.8470. Min Act: -0.1700
Data Index: 2206732 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9720. Min Range: -6.9720
Max Act: 6.6908. Min Act: -0.1700
Data Index: 7794399 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9720. Min Range: -6.9720
Max Act: 6.5345. Min Act: -0.1700
Data Index: 3624052 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9720. Min Range: -6.9720
Max Act: 6.4720. Min Act: -0.1700
Data Index: 7794400 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9720. Min Range: -6.9720
Max Act: 6.4095. Min Act: -0.1700
Data Index: 1059527 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9720. Min Range: -6.9720
Max Act: 6.4095. Min Act: -0.1700
Data Index: 6729454 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9720. Min Range: -6.9720
Max Act: 6.3470. Min Act: -0.1700
Data Index: 2369995 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9720. Min Range: -6.9720
Max Act: 6.2533. Min Act: -0.1700
Data Index: 225421 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9720. Min Range: -6.9720
Max Act: 6.2533. Min Act: -0.1700
Data Index: 7488819 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9720. Min Range: -6.9720
Max Act: 6.2845. Min Act: -0.1700
Data Index: 4545969 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9720. Min Range: -6.9720
Max Act: 6.2533. Min Act: -0.1700
Data Index: 5779973 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9720. Min Range: -6.9720
Max Act: 6.2220. Min Act: -0.1700
Data Index: 6909823 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9720. Min Range: -6.9720
Max Act: 6.2533. Min Act: -0.1700
Data Index: 4182307 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9720. Min Range: -6.9720
Max Act: 6.2220. Min Act: -0.1700
Data Index: 2199323 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9720. Min Range: -6.9720
Max Act: 6.1908. Min Act: -0.1700
Data Index: 4516115 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9720. Min Range: -6.9720
Max Act: 6.1908. Min Act: -0.1700
Data Index: 3564210 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9720. Min Range: -6.9720
Max Act: 6.1908. Min Act: -0.1700
Data Index: 818854 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9720. Min Range: -6.9720
Max Act: 6.1283. Min Act: -0.1700
Data Index: 3220532 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9720. Min Range: -6.9720
Max Act: 6.1595. Min Act: -0.1700
Data Index: 5070936 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #19