Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4674 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0630. Min Range: -6.0630
Max Act: 6.0630. Min Act: -0.1700
Data Index: 1939359 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0630. Min Range: -6.0630
Max Act: 5.9380. Min Act: -0.1700
Data Index: 8312621 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0630. Min Range: -6.0630
Max Act: 5.8755. Min Act: -0.1700
Data Index: 2444565 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0630. Min Range: -6.0630
Max Act: 5.7817. Min Act: -0.1700
Data Index: 6204394 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0630. Min Range: -6.0630
Max Act: 5.7505. Min Act: -0.1700
Data Index: 2186022 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0630. Min Range: -6.0630
Max Act: 5.7192. Min Act: -0.1700
Data Index: 5040429 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0630. Min Range: -6.0630
Max Act: 5.6255. Min Act: -0.1700
Data Index: 573587 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0630. Min Range: -6.0630
Max Act: 5.6567. Min Act: -0.1700
Data Index: 2709562 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0630. Min Range: -6.0630
Max Act: 5.5942. Min Act: -0.1700
Data Index: 7478186 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0630. Min Range: -6.0630
Max Act: 5.5630. Min Act: -0.1700
Data Index: 6913466 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0630. Min Range: -6.0630
Max Act: 5.5630. Min Act: -0.1700
Data Index: 5714014 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0630. Min Range: -6.0630
Max Act: 5.5005. Min Act: -0.1700
Data Index: 7207429 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0630. Min Range: -6.0630
Max Act: 5.5005. Min Act: -0.1700
Data Index: 4705721 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0630. Min Range: -6.0630
Max Act: 5.5005. Min Act: -0.1700
Data Index: 4241223 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0630. Min Range: -6.0630
Max Act: 5.5005. Min Act: -0.1700
Data Index: 4020661 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0630. Min Range: -6.0630
Max Act: 5.4692. Min Act: -0.1700
Data Index: 3523757 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0630. Min Range: -6.0630
Max Act: 5.4692. Min Act: -0.1700
Data Index: 7849499 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0630. Min Range: -6.0630
Max Act: 5.4692. Min Act: -0.1700
Data Index: 6299571 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0630. Min Range: -6.0630
Max Act: 5.4692. Min Act: -0.1700
Data Index: 5137778 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0630. Min Range: -6.0630
Max Act: 5.4380. Min Act: -0.1700
Data Index: 540899 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #19