Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1957 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0466. Min Range: -6.0466
Max Act: 6.0466. Min Act: -0.1700
Data Index: 4160698 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0466. Min Range: -6.0466
Max Act: 6.0153. Min Act: -0.1700
Data Index: 6468702 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0466. Min Range: -6.0466
Max Act: 5.9216. Min Act: -0.1700
Data Index: 5314861 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0466. Min Range: -6.0466
Max Act: 5.8903. Min Act: -0.1700
Data Index: 8397782 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0466. Min Range: -6.0466
Max Act: 5.8903. Min Act: -0.1700
Data Index: 3841993 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0466. Min Range: -6.0466
Max Act: 5.8903. Min Act: -0.1700
Data Index: 4896197 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0466. Min Range: -6.0466
Max Act: 5.8591. Min Act: -0.1700
Data Index: 1520983 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0466. Min Range: -6.0466
Max Act: 5.8278. Min Act: -0.1700
Data Index: 2564872 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0466. Min Range: -6.0466
Max Act: 5.7966. Min Act: -0.1700
Data Index: 8528982 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0466. Min Range: -6.0466
Max Act: 5.7653. Min Act: -0.1700
Data Index: 7312692 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0466. Min Range: -6.0466
Max Act: 5.7966. Min Act: -0.1700
Data Index: 2846401 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0466. Min Range: -6.0466
Max Act: 5.7966. Min Act: -0.1700
Data Index: 6059963 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0466. Min Range: -6.0466
Max Act: 5.7653. Min Act: -0.1700
Data Index: 1358097 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0466. Min Range: -6.0466
Max Act: 5.7653. Min Act: -0.1700
Data Index: 5801021 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0466. Min Range: -6.0466
Max Act: 5.7653. Min Act: -0.1700
Data Index: 4902275 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0466. Min Range: -6.0466
Max Act: 5.7341. Min Act: -0.1700
Data Index: 3591319 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0466. Min Range: -6.0466
Max Act: 5.7653. Min Act: -0.1700
Data Index: 6966536 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0466. Min Range: -6.0466
Max Act: 5.7341. Min Act: -0.1700
Data Index: 3895720 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0466. Min Range: -6.0466
Max Act: 5.7341. Min Act: -0.1700
Data Index: 1961996 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0466. Min Range: -6.0466
Max Act: 5.7028. Min Act: -0.1700
Data Index: 4629056 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #19