Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3523 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1716. Min Range: -7.1716
Max Act: 7.1716. Min Act: -0.1700
Data Index: 1152863 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1716. Min Range: -7.1716
Max Act: 6.7654. Min Act: -0.1700
Data Index: 6446730 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1716. Min Range: -7.1716
Max Act: 6.6091. Min Act: -0.1700
Data Index: 2832906 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1716. Min Range: -7.1716
Max Act: 6.6404. Min Act: -0.1700
Data Index: 6046705 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1716. Min Range: -7.1716
Max Act: 6.6404. Min Act: -0.1700
Data Index: 3929157 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1716. Min Range: -7.1716
Max Act: 6.4529. Min Act: -0.1700
Data Index: 6036052 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1716. Min Range: -7.1716
Max Act: 6.4216. Min Act: -0.1700
Data Index: 6197818 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1716. Min Range: -7.1716
Max Act: 6.4216. Min Act: -0.1700
Data Index: 1943409 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1716. Min Range: -7.1716
Max Act: 6.3904. Min Act: -0.1700
Data Index: 5435519 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1716. Min Range: -7.1716
Max Act: 6.3904. Min Act: -0.1700
Data Index: 5833720 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1716. Min Range: -7.1716
Max Act: 6.3591. Min Act: -0.1700
Data Index: 1704354 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1716. Min Range: -7.1716
Max Act: 6.3279. Min Act: -0.1700
Data Index: 4481542 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1716. Min Range: -7.1716
Max Act: 6.3279. Min Act: -0.1700
Data Index: 4649664 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1716. Min Range: -7.1716
Max Act: 6.2966. Min Act: -0.1700
Data Index: 5096199 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1716. Min Range: -7.1716
Max Act: 6.2966. Min Act: -0.1700
Data Index: 2406499 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1716. Min Range: -7.1716
Max Act: 6.2654. Min Act: -0.1700
Data Index: 7727378 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1716. Min Range: -7.1716
Max Act: 6.2654. Min Act: -0.1700
Data Index: 379109 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1716. Min Range: -7.1716
Max Act: 6.2341. Min Act: -0.1700
Data Index: 568737 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1716. Min Range: -7.1716
Max Act: 6.2341. Min Act: -0.1700
Data Index: 4133547 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1716. Min Range: -7.1716
Max Act: 6.2341. Min Act: -0.1700
Data Index: 5252098 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #19