Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 28 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7263. Min Range: -7.7263
Max Act: 7.7263. Min Act: -0.1700
Data Index: 5314415 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7263. Min Range: -7.7263
Max Act: 7.0700. Min Act: -0.1700
Data Index: 2309529 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7263. Min Range: -7.7263
Max Act: 7.0075. Min Act: -0.1700
Data Index: 7277684 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7263. Min Range: -7.7263
Max Act: 7.0075. Min Act: -0.1700
Data Index: 6297350 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7263. Min Range: -7.7263
Max Act: 7.0075. Min Act: -0.1700
Data Index: 710775 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7263. Min Range: -7.7263
Max Act: 6.9138. Min Act: -0.1700
Data Index: 402961 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7263. Min Range: -7.7263
Max Act: 6.8825. Min Act: -0.1700
Data Index: 1975547 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7263. Min Range: -7.7263
Max Act: 6.8513. Min Act: -0.1700
Data Index: 2817813 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7263. Min Range: -7.7263
Max Act: 6.8825. Min Act: -0.1700
Data Index: 8733343 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7263. Min Range: -7.7263
Max Act: 6.8200. Min Act: -0.1700
Data Index: 2279510 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7263. Min Range: -7.7263
Max Act: 6.7888. Min Act: -0.1700
Data Index: 1305220 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7263. Min Range: -7.7263
Max Act: 6.7888. Min Act: -0.1700
Data Index: 8272753 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7263. Min Range: -7.7263
Max Act: 6.7888. Min Act: -0.1700
Data Index: 8322037 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7263. Min Range: -7.7263
Max Act: 6.7263. Min Act: -0.1700
Data Index: 3206053 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7263. Min Range: -7.7263
Max Act: 6.7263. Min Act: -0.1700
Data Index: 123090 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7263. Min Range: -7.7263
Max Act: 6.7263. Min Act: -0.1700
Data Index: 753999 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7263. Min Range: -7.7263
Max Act: 6.6950. Min Act: -0.1700
Data Index: 3406978 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7263. Min Range: -7.7263
Max Act: 6.6325. Min Act: -0.1700
Data Index: 7900311 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7263. Min Range: -7.7263
Max Act: 6.6325. Min Act: -0.1700
Data Index: 3822161 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7263. Min Range: -7.7263
Max Act: 6.6325. Min Act: -0.1700
Data Index: 4583092 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #19