Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3146 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1253. Min Range: -4.1253
Max Act: 4.0940. Min Act: -0.1700
Data Index: 1170086 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1253. Min Range: -4.1253
Max Act: 4.1253. Min Act: -0.1700
Data Index: 2488030 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1253. Min Range: -4.1253
Max Act: 4.0940. Min Act: -0.1700
Data Index: 3207448 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1253. Min Range: -4.1253
Max Act: 4.0315. Min Act: -0.1700
Data Index: 7442549 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1253. Min Range: -4.1253
Max Act: 4.0002. Min Act: -0.1700
Data Index: 3081219 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1253. Min Range: -4.1253
Max Act: 4.0002. Min Act: -0.1700
Data Index: 3207443 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1253. Min Range: -4.1253
Max Act: 4.0002. Min Act: -0.1700
Data Index: 1817800 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1253. Min Range: -4.1253
Max Act: 4.0002. Min Act: -0.1700
Data Index: 7595999 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1253. Min Range: -4.1253
Max Act: 3.9690. Min Act: -0.1700
Data Index: 6994693 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1253. Min Range: -4.1253
Max Act: 3.9690. Min Act: -0.1700
Data Index: 3207451 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1253. Min Range: -4.1253
Max Act: 3.9690. Min Act: -0.1700
Data Index: 5265190 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1253. Min Range: -4.1253
Max Act: 3.9690. Min Act: -0.1700
Data Index: 5820876 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1253. Min Range: -4.1253
Max Act: 3.9377. Min Act: -0.1700
Data Index: 3013716 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1253. Min Range: -4.1253
Max Act: 3.9377. Min Act: -0.1700
Data Index: 7727 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1253. Min Range: -4.1253
Max Act: 3.9377. Min Act: -0.1700
Data Index: 8276677 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1253. Min Range: -4.1253
Max Act: 3.9377. Min Act: -0.1700
Data Index: 2630566 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1253. Min Range: -4.1253
Max Act: 3.9377. Min Act: -0.1700
Data Index: 1932652 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1253. Min Range: -4.1253
Max Act: 3.9377. Min Act: -0.1700
Data Index: 3207450 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1253. Min Range: -4.1253
Max Act: 3.9377. Min Act: -0.1700
Data Index: 5826303 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1253. Min Range: -4.1253
Max Act: 3.9064. Min Act: -0.1700
Data Index: 2693671 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #19