Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3097 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6263. Min Range: -5.6263
Max Act: 5.6263. Min Act: -0.1700
Data Index: 5506808 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6263. Min Range: -5.6263
Max Act: 5.5951. Min Act: -0.1700
Data Index: 6729180 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6263. Min Range: -5.6263
Max Act: 5.5638. Min Act: -0.1700
Data Index: 6715249 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6263. Min Range: -5.6263
Max Act: 5.3451. Min Act: -0.1700
Data Index: 6729176 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6263. Min Range: -5.6263
Max Act: 5.3138. Min Act: -0.1700
Data Index: 2043849 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6263. Min Range: -5.6263
Max Act: 5.3138. Min Act: -0.1700
Data Index: 1039850 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6263. Min Range: -5.6263
Max Act: 5.2513. Min Act: -0.1700
Data Index: 5776287 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6263. Min Range: -5.6263
Max Act: 5.2513. Min Act: -0.1700
Data Index: 2624545 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6263. Min Range: -5.6263
Max Act: 5.2201. Min Act: -0.1700
Data Index: 174819 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6263. Min Range: -5.6263
Max Act: 5.2201. Min Act: -0.1700
Data Index: 7186722 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6263. Min Range: -5.6263
Max Act: 5.1888. Min Act: -0.1700
Data Index: 5556009 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6263. Min Range: -5.6263
Max Act: 5.2201. Min Act: -0.1700
Data Index: 1040336 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6263. Min Range: -5.6263
Max Act: 5.1888. Min Act: -0.1700
Data Index: 1817246 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6263. Min Range: -5.6263
Max Act: 5.1576. Min Act: -0.1700
Data Index: 175955 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6263. Min Range: -5.6263
Max Act: 5.1576. Min Act: -0.1700
Data Index: 4825170 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6263. Min Range: -5.6263
Max Act: 5.1576. Min Act: -0.1700
Data Index: 7186726 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6263. Min Range: -5.6263
Max Act: 5.1576. Min Act: -0.1700
Data Index: 606098 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6263. Min Range: -5.6263
Max Act: 5.1576. Min Act: -0.1700
Data Index: 3936833 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6263. Min Range: -5.6263
Max Act: 5.1263. Min Act: -0.1700
Data Index: 3177117 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6263. Min Range: -5.6263
Max Act: 5.1263. Min Act: -0.1700
Data Index: 6968851 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #19