Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3296 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.5614. Min Act: -0.1700
Data Index: 1795903 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.3427. Min Act: -0.1700
Data Index: 3062505 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.3114. Min Act: -0.1700
Data Index: 4437810 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.2802. Min Act: -0.1700
Data Index: 1973652 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.2489. Min Act: -0.1700
Data Index: 4932872 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.1552. Min Act: -0.1700
Data Index: 3245938 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.0927. Min Act: -0.1700
Data Index: 4674603 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5614. Min Range: -6.5614
Max Act: 5.9989. Min Act: -0.1700
Data Index: 331346 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.0302. Min Act: -0.1700
Data Index: 5088861 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.0302. Min Act: -0.1700
Data Index: 5143729 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.0614. Min Act: -0.1700
Data Index: 3336683 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5614. Min Range: -6.5614
Max Act: 5.9989. Min Act: -0.1700
Data Index: 5578662 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5614. Min Range: -6.5614
Max Act: 5.9989. Min Act: -0.1700
Data Index: 3456294 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5614. Min Range: -6.5614
Max Act: 5.9989. Min Act: -0.1700
Data Index: 8576548 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5614. Min Range: -6.5614
Max Act: 5.9989. Min Act: -0.1700
Data Index: 6875911 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5614. Min Range: -6.5614
Max Act: 5.9364. Min Act: -0.1700
Data Index: 3097417 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5614. Min Range: -6.5614
Max Act: 5.9052. Min Act: -0.1700
Data Index: 1413453 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5614. Min Range: -6.5614
Max Act: 5.9052. Min Act: -0.1700
Data Index: 4986317 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5614. Min Range: -6.5614
Max Act: 5.9052. Min Act: -0.1700
Data Index: 1125536 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5614. Min Range: -6.5614
Max Act: 5.8739. Min Act: -0.1700
Data Index: 295514 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #19