Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4102 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9418. Min Range: -5.9418
Max Act: 5.9418. Min Act: -0.1700
Data Index: 4961236 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9418. Min Range: -5.9418
Max Act: 5.8793. Min Act: -0.1700
Data Index: 6656649 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9418. Min Range: -5.9418
Max Act: 5.9105. Min Act: -0.1700
Data Index: 7944898 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9418. Min Range: -5.9418
Max Act: 5.8168. Min Act: -0.1700
Data Index: 5551600 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9418. Min Range: -5.9418
Max Act: 5.7230. Min Act: -0.1700
Data Index: 5148894 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9418. Min Range: -5.9418
Max Act: 5.6605. Min Act: -0.1700
Data Index: 7223367 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9418. Min Range: -5.9418
Max Act: 5.6918. Min Act: -0.1700
Data Index: 3511426 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9418. Min Range: -5.9418
Max Act: 5.6605. Min Act: -0.1700
Data Index: 488704 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9418. Min Range: -5.9418
Max Act: 5.6605. Min Act: -0.1700
Data Index: 7950882 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9418. Min Range: -5.9418
Max Act: 5.6293. Min Act: -0.1700
Data Index: 926412 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9418. Min Range: -5.9418
Max Act: 5.6293. Min Act: -0.1700
Data Index: 7142180 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9418. Min Range: -5.9418
Max Act: 5.6293. Min Act: -0.1700
Data Index: 6498007 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9418. Min Range: -5.9418
Max Act: 5.5980. Min Act: -0.1700
Data Index: 7036144 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9418. Min Range: -5.9418
Max Act: 5.6293. Min Act: -0.1700
Data Index: 7498419 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9418. Min Range: -5.9418
Max Act: 5.5980. Min Act: -0.1700
Data Index: 448747 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9418. Min Range: -5.9418
Max Act: 5.5980. Min Act: -0.1700
Data Index: 5283965 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9418. Min Range: -5.9418
Max Act: 5.5980. Min Act: -0.1700
Data Index: 3511427 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9418. Min Range: -5.9418
Max Act: 5.5980. Min Act: -0.1700
Data Index: 3243566 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9418. Min Range: -5.9418
Max Act: 5.5355. Min Act: -0.1700
Data Index: 2878743 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9418. Min Range: -5.9418
Max Act: 5.5355. Min Act: -0.1700
Data Index: 2086840 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #19