Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6344 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9546. Min Range: -5.9546
Max Act: 5.9546. Min Act: -0.1700
Data Index: 2513073 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9546. Min Range: -5.9546
Max Act: 5.9546. Min Act: -0.1700
Data Index: 3021088 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9546. Min Range: -5.9546
Max Act: 5.6734. Min Act: -0.1700
Data Index: 4359783 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9546. Min Range: -5.9546
Max Act: 5.6421. Min Act: -0.1700
Data Index: 6892555 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9546. Min Range: -5.9546
Max Act: 5.5796. Min Act: -0.1700
Data Index: 3058374 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9546. Min Range: -5.9546
Max Act: 5.5171. Min Act: -0.1700
Data Index: 2567241 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9546. Min Range: -5.9546
Max Act: 5.4546. Min Act: -0.1700
Data Index: 6163395 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9546. Min Range: -5.9546
Max Act: 5.4546. Min Act: -0.1700
Data Index: 5180741 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9546. Min Range: -5.9546
Max Act: 5.3921. Min Act: -0.1700
Data Index: 4755874 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9546. Min Range: -5.9546
Max Act: 5.3609. Min Act: -0.1700
Data Index: 4259385 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9546. Min Range: -5.9546
Max Act: 5.3296. Min Act: -0.1700
Data Index: 5940141 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9546. Min Range: -5.9546
Max Act: 5.2984. Min Act: -0.1700
Data Index: 4279085 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9546. Min Range: -5.9546
Max Act: 5.2671. Min Act: -0.1700
Data Index: 1276640 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9546. Min Range: -5.9546
Max Act: 5.2671. Min Act: -0.1700
Data Index: 1491460 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9546. Min Range: -5.9546
Max Act: 5.2359. Min Act: -0.1700
Data Index: 1461538 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9546. Min Range: -5.9546
Max Act: 5.2671. Min Act: -0.1700
Data Index: 2582480 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9546. Min Range: -5.9546
Max Act: 5.2671. Min Act: -0.1700
Data Index: 6699465 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9546. Min Range: -5.9546
Max Act: 5.2359. Min Act: -0.1700
Data Index: 3537636 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9546. Min Range: -5.9546
Max Act: 5.2359. Min Act: -0.1700
Data Index: 3537635 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9546. Min Range: -5.9546
Max Act: 5.2359. Min Act: -0.1700
Data Index: 6415411 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #19