Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2722 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4366. Min Range: -4.4366
Max Act: 4.4366. Min Act: -0.1700
Data Index: 8789902 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4366. Min Range: -4.4366
Max Act: 4.3429. Min Act: -0.1700
Data Index: 4509463 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4366. Min Range: -4.4366
Max Act: 4.3741. Min Act: -0.1700
Data Index: 6578912 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4366. Min Range: -4.4366
Max Act: 4.3429. Min Act: -0.1700
Data Index: 4300544 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4366. Min Range: -4.4366
Max Act: 4.3116. Min Act: -0.1700
Data Index: 1100035 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4366. Min Range: -4.4366
Max Act: 4.2804. Min Act: -0.1700
Data Index: 5659962 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4366. Min Range: -4.4366
Max Act: 4.2804. Min Act: -0.1700
Data Index: 3425220 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4366. Min Range: -4.4366
Max Act: 4.2491. Min Act: -0.1700
Data Index: 1412411 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4366. Min Range: -4.4366
Max Act: 4.2491. Min Act: -0.1700
Data Index: 8228310 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4366. Min Range: -4.4366
Max Act: 4.2491. Min Act: -0.1700
Data Index: 2008056 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4366. Min Range: -4.4366
Max Act: 4.2491. Min Act: -0.1700
Data Index: 7567216 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4366. Min Range: -4.4366
Max Act: 4.2491. Min Act: -0.1700
Data Index: 1755792 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4366. Min Range: -4.4366
Max Act: 4.2179. Min Act: -0.1700
Data Index: 3025630 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4366. Min Range: -4.4366
Max Act: 4.2179. Min Act: -0.1700
Data Index: 1245155 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4366. Min Range: -4.4366
Max Act: 4.1866. Min Act: -0.1700
Data Index: 3425218 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4366. Min Range: -4.4366
Max Act: 4.1866. Min Act: -0.1700
Data Index: 6786251 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4366. Min Range: -4.4366
Max Act: 4.2179. Min Act: -0.1700
Data Index: 4342187 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4366. Min Range: -4.4366
Max Act: 4.1866. Min Act: -0.1700
Data Index: 1628666 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4366. Min Range: -4.4366
Max Act: 4.1866. Min Act: -0.1700
Data Index: 3328015 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4366. Min Range: -4.4366
Max Act: 4.1553. Min Act: -0.1700
Data Index: 1910554 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #19