Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 742 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2721. Min Range: -5.2721
Max Act: 5.2721. Min Act: -0.1700
Data Index: 4813389 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2721. Min Range: -5.2721
Max Act: 5.2721. Min Act: -0.1700
Data Index: 434174 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2721. Min Range: -5.2721
Max Act: 5.2409. Min Act: -0.1700
Data Index: 2960223 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2721. Min Range: -5.2721
Max Act: 5.2096. Min Act: -0.1700
Data Index: 1399847 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2721. Min Range: -5.2721
Max Act: 5.0846. Min Act: -0.1700
Data Index: 7105893 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2721. Min Range: -5.2721
Max Act: 5.1159. Min Act: -0.1700
Data Index: 4584533 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2721. Min Range: -5.2721
Max Act: 5.0846. Min Act: -0.1700
Data Index: 7844171 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2721. Min Range: -5.2721
Max Act: 5.0846. Min Act: -0.1700
Data Index: 3133984 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2721. Min Range: -5.2721
Max Act: 5.0846. Min Act: -0.1700
Data Index: 3182230 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2721. Min Range: -5.2721
Max Act: 5.0846. Min Act: -0.1700
Data Index: 507092 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2721. Min Range: -5.2721
Max Act: 5.0846. Min Act: -0.1700
Data Index: 7752398 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2721. Min Range: -5.2721
Max Act: 5.0534. Min Act: -0.1700
Data Index: 4393110 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2721. Min Range: -5.2721
Max Act: 5.0534. Min Act: -0.1700
Data Index: 5949100 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2721. Min Range: -5.2721
Max Act: 5.0534. Min Act: -0.1700
Data Index: 8653436 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2721. Min Range: -5.2721
Max Act: 5.0534. Min Act: -0.1700
Data Index: 2244856 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2721. Min Range: -5.2721
Max Act: 5.0534. Min Act: -0.1700
Data Index: 7314465 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2721. Min Range: -5.2721
Max Act: 5.0221. Min Act: -0.1700
Data Index: 6440959 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2721. Min Range: -5.2721
Max Act: 5.0221. Min Act: -0.1700
Data Index: 6483162 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2721. Min Range: -5.2721
Max Act: 5.0534. Min Act: -0.1700
Data Index: 1782447 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2721. Min Range: -5.2721
Max Act: 5.0221. Min Act: -0.1700
Data Index: 6701571 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19