Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3538 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9843. Min Range: -5.9843
Max Act: 5.9843. Min Act: -0.1700
Data Index: 7745439 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9843. Min Range: -5.9843
Max Act: 5.7343. Min Act: -0.1700
Data Index: 2737714 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9843. Min Range: -5.9843
Max Act: 5.6093. Min Act: -0.1700
Data Index: 360671 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9843. Min Range: -5.9843
Max Act: 5.5468. Min Act: -0.1700
Data Index: 1275101 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9843. Min Range: -5.9843
Max Act: 5.5155. Min Act: -0.1700
Data Index: 111739 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9843. Min Range: -5.9843
Max Act: 5.4843. Min Act: -0.1700
Data Index: 5047415 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9843. Min Range: -5.9843
Max Act: 5.4530. Min Act: -0.1700
Data Index: 4827258 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9843. Min Range: -5.9843
Max Act: 5.3905. Min Act: -0.1700
Data Index: 5952717 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9843. Min Range: -5.9843
Max Act: 5.4218. Min Act: -0.1700
Data Index: 7963775 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9843. Min Range: -5.9843
Max Act: 5.4218. Min Act: -0.1700
Data Index: 1880055 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9843. Min Range: -5.9843
Max Act: 5.3593. Min Act: -0.1700
Data Index: 3283543 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9843. Min Range: -5.9843
Max Act: 5.3905. Min Act: -0.1700
Data Index: 392009 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9843. Min Range: -5.9843
Max Act: 5.3593. Min Act: -0.1700
Data Index: 4680056 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9843. Min Range: -5.9843
Max Act: 5.3280. Min Act: -0.1700
Data Index: 7656567 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9843. Min Range: -5.9843
Max Act: 5.3905. Min Act: -0.1700
Data Index: 5965596 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9843. Min Range: -5.9843
Max Act: 5.3593. Min Act: -0.1700
Data Index: 5363045 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9843. Min Range: -5.9843
Max Act: 5.3593. Min Act: -0.1700
Data Index: 5237503 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9843. Min Range: -5.9843
Max Act: 5.3280. Min Act: -0.1700
Data Index: 4328060 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9843. Min Range: -5.9843
Max Act: 5.3280. Min Act: -0.1700
Data Index: 4586636 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9843. Min Range: -5.9843
Max Act: 5.3280. Min Act: -0.1700
Data Index: 3262931 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19