Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3768 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1919. Min Range: -5.1919
Max Act: 5.1919. Min Act: -0.1700
Data Index: 5780195 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1919. Min Range: -5.1919
Max Act: 5.1607. Min Act: -0.1700
Data Index: 1659104 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1919. Min Range: -5.1919
Max Act: 5.1607. Min Act: -0.1700
Data Index: 36772 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1919. Min Range: -5.1919
Max Act: 5.0982. Min Act: -0.1700
Data Index: 1250264 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1919. Min Range: -5.1919
Max Act: 5.0669. Min Act: -0.1700
Data Index: 745045 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1919. Min Range: -5.1919
Max Act: 5.0357. Min Act: -0.1700
Data Index: 5996770 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1919. Min Range: -5.1919
Max Act: 5.0044. Min Act: -0.1700
Data Index: 2297795 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1919. Min Range: -5.1919
Max Act: 5.0044. Min Act: -0.1700
Data Index: 6468791 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1919. Min Range: -5.1919
Max Act: 5.0357. Min Act: -0.1700
Data Index: 825948 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1919. Min Range: -5.1919
Max Act: 4.9732. Min Act: -0.1700
Data Index: 5579518 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1919. Min Range: -5.1919
Max Act: 4.9732. Min Act: -0.1700
Data Index: 2449569 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1919. Min Range: -5.1919
Max Act: 4.9419. Min Act: -0.1700
Data Index: 5852280 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1919. Min Range: -5.1919
Max Act: 4.9732. Min Act: -0.1700
Data Index: 4456764 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1919. Min Range: -5.1919
Max Act: 4.9732. Min Act: -0.1700
Data Index: 8681 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1919. Min Range: -5.1919
Max Act: 4.9107. Min Act: -0.1700
Data Index: 5606828 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1919. Min Range: -5.1919
Max Act: 4.9419. Min Act: -0.1700
Data Index: 6687718 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1919. Min Range: -5.1919
Max Act: 4.9419. Min Act: -0.1700
Data Index: 5144123 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1919. Min Range: -5.1919
Max Act: 4.9107. Min Act: -0.1700
Data Index: 5450562 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1919. Min Range: -5.1919
Max Act: 4.9107. Min Act: -0.1700
Data Index: 2943792 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1919. Min Range: -5.1919
Max Act: 4.8794. Min Act: -0.1700
Data Index: 4628965 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #19