Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2103 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0407. Min Range: -6.0407
Max Act: 6.0407. Min Act: -0.1700
Data Index: 1988992 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0407. Min Range: -6.0407
Max Act: 5.9157. Min Act: -0.1700
Data Index: 5183765 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0407. Min Range: -6.0407
Max Act: 5.8220. Min Act: -0.1700
Data Index: 6953882 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0407. Min Range: -6.0407
Max Act: 5.7907. Min Act: -0.1700
Data Index: 7307157 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0407. Min Range: -6.0407
Max Act: 5.7595. Min Act: -0.1700
Data Index: 6062944 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0407. Min Range: -6.0407
Max Act: 5.7282. Min Act: -0.1700
Data Index: 5100064 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0407. Min Range: -6.0407
Max Act: 5.6970. Min Act: -0.1700
Data Index: 8235860 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0407. Min Range: -6.0407
Max Act: 5.6970. Min Act: -0.1700
Data Index: 7753899 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0407. Min Range: -6.0407
Max Act: 5.6657. Min Act: -0.1700
Data Index: 5405793 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0407. Min Range: -6.0407
Max Act: 5.6345. Min Act: -0.1700
Data Index: 3990498 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0407. Min Range: -6.0407
Max Act: 5.6345. Min Act: -0.1700
Data Index: 4436181 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0407. Min Range: -6.0407
Max Act: 5.6032. Min Act: -0.1700
Data Index: 5423534 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0407. Min Range: -6.0407
Max Act: 5.5720. Min Act: -0.1700
Data Index: 6708689 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0407. Min Range: -6.0407
Max Act: 5.6032. Min Act: -0.1700
Data Index: 7657396 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0407. Min Range: -6.0407
Max Act: 5.6032. Min Act: -0.1700
Data Index: 5065713 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0407. Min Range: -6.0407
Max Act: 5.6032. Min Act: -0.1700
Data Index: 8316853 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0407. Min Range: -6.0407
Max Act: 5.5407. Min Act: -0.1700
Data Index: 69430 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0407. Min Range: -6.0407
Max Act: 5.5720. Min Act: -0.1700
Data Index: 7255562 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0407. Min Range: -6.0407
Max Act: 5.5720. Min Act: -0.1700
Data Index: 5369521 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0407. Min Range: -6.0407
Max Act: 5.5720. Min Act: -0.1700
Data Index: 111367 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #19