Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2348 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2793. Min Range: -4.2793
Max Act: 4.2793. Min Act: -0.1700
Data Index: 1281631 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2793. Min Range: -4.2793
Max Act: 4.0917. Min Act: -0.1700
Data Index: 8388051 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2793. Min Range: -4.2793
Max Act: 4.0292. Min Act: -0.1700
Data Index: 7909999 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2793. Min Range: -4.2793
Max Act: 3.9980. Min Act: -0.1700
Data Index: 8500084 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2793. Min Range: -4.2793
Max Act: 3.9354. Min Act: -0.1700
Data Index: 8266867 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2793. Min Range: -4.2793
Max Act: 3.9667. Min Act: -0.1700
Data Index: 893847 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2793. Min Range: -4.2793
Max Act: 3.9354. Min Act: -0.1700
Data Index: 2046096 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2793. Min Range: -4.2793
Max Act: 3.9354. Min Act: -0.1700
Data Index: 2508648 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2793. Min Range: -4.2793
Max Act: 3.9042. Min Act: -0.1700
Data Index: 3640870 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2793. Min Range: -4.2793
Max Act: 3.8729. Min Act: -0.1700
Data Index: 2739057 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2793. Min Range: -4.2793
Max Act: 3.8416. Min Act: -0.1700
Data Index: 5943056 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2793. Min Range: -4.2793
Max Act: 3.8729. Min Act: -0.1700
Data Index: 2657729 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2793. Min Range: -4.2793
Max Act: 3.8416. Min Act: -0.1700
Data Index: 263842 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2793. Min Range: -4.2793
Max Act: 3.8729. Min Act: -0.1700
Data Index: 7599702 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2793. Min Range: -4.2793
Max Act: 3.8416. Min Act: -0.1700
Data Index: 2672969 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2793. Min Range: -4.2793
Max Act: 3.8104. Min Act: -0.1700
Data Index: 4245536 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2793. Min Range: -4.2793
Max Act: 3.7791. Min Act: -0.1700
Data Index: 598736 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2793. Min Range: -4.2793
Max Act: 3.7791. Min Act: -0.1700
Data Index: 3597243 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2793. Min Range: -4.2793
Max Act: 3.8104. Min Act: -0.1700
Data Index: 5300901 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2793. Min Range: -4.2793
Max Act: 3.7791. Min Act: -0.1700
Data Index: 5836342 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19