Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2579 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4541. Min Range: -8.4541
Max Act: 8.4541. Min Act: -0.1700
Data Index: 8362964 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4541. Min Range: -8.4541
Max Act: 8.3291. Min Act: -0.1700
Data Index: 7082955 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4541. Min Range: -8.4541
Max Act: 8.2666. Min Act: -0.1700
Data Index: 5029689 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4541. Min Range: -8.4541
Max Act: 8.2041. Min Act: -0.1700
Data Index: 6853942 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4541. Min Range: -8.4541
Max Act: 8.1416. Min Act: -0.1700
Data Index: 709411 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4541. Min Range: -8.4541
Max Act: 7.9228. Min Act: -0.1700
Data Index: 2224400 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4541. Min Range: -8.4541
Max Act: 7.7666. Min Act: -0.1700
Data Index: 4032289 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4541. Min Range: -8.4541
Max Act: 7.7041. Min Act: -0.1700
Data Index: 321619 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4541. Min Range: -8.4541
Max Act: 7.7041. Min Act: -0.1700
Data Index: 6961356 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4541. Min Range: -8.4541
Max Act: 7.7041. Min Act: -0.1700
Data Index: 2362842 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4541. Min Range: -8.4541
Max Act: 7.7041. Min Act: -0.1700
Data Index: 7702149 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4541. Min Range: -8.4541
Max Act: 7.6728. Min Act: -0.1700
Data Index: 2075572 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4541. Min Range: -8.4541
Max Act: 7.6416. Min Act: -0.1700
Data Index: 5029690 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4541. Min Range: -8.4541
Max Act: 7.6728. Min Act: -0.1700
Data Index: 2087340 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4541. Min Range: -8.4541
Max Act: 7.6103. Min Act: -0.1700
Data Index: 4265324 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4541. Min Range: -8.4541
Max Act: 7.6103. Min Act: -0.1700
Data Index: 7230141 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4541. Min Range: -8.4541
Max Act: 7.5791. Min Act: -0.1700
Data Index: 2530298 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4541. Min Range: -8.4541
Max Act: 7.5791. Min Act: -0.1700
Data Index: 2336404 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4541. Min Range: -8.4541
Max Act: 7.5166. Min Act: -0.1700
Data Index: 4176911 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4541. Min Range: -8.4541
Max Act: 7.5478. Min Act: -0.1700
Data Index: 557882 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #19