Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2428 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7285. Min Range: -6.7285
Max Act: 6.7285. Min Act: -0.1700
Data Index: 1544753 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7285. Min Range: -6.7285
Max Act: 6.7285. Min Act: -0.1700
Data Index: 1683309 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7285. Min Range: -6.7285
Max Act: 6.7285. Min Act: -0.1700
Data Index: 2738345 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7285. Min Range: -6.7285
Max Act: 6.7285. Min Act: -0.1700
Data Index: 2181486 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7285. Min Range: -6.7285
Max Act: 6.6973. Min Act: -0.1700
Data Index: 6378122 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7285. Min Range: -6.7285
Max Act: 6.6660. Min Act: -0.1700
Data Index: 2513527 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7285. Min Range: -6.7285
Max Act: 6.6035. Min Act: -0.1700
Data Index: 3080618 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7285. Min Range: -6.7285
Max Act: 6.5723. Min Act: -0.1700
Data Index: 5071492 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7285. Min Range: -6.7285
Max Act: 6.5723. Min Act: -0.1700
Data Index: 362980 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7285. Min Range: -6.7285
Max Act: 6.5723. Min Act: -0.1700
Data Index: 8664111 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7285. Min Range: -6.7285
Max Act: 6.5723. Min Act: -0.1700
Data Index: 5117615 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7285. Min Range: -6.7285
Max Act: 6.5098. Min Act: -0.1700
Data Index: 7885312 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7285. Min Range: -6.7285
Max Act: 6.4785. Min Act: -0.1700
Data Index: 455891 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7285. Min Range: -6.7285
Max Act: 6.4473. Min Act: -0.1700
Data Index: 7203700 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7285. Min Range: -6.7285
Max Act: 6.4473. Min Act: -0.1700
Data Index: 4238830 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7285. Min Range: -6.7285
Max Act: 6.4160. Min Act: -0.1699
Data Index: 3923254 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7285. Min Range: -6.7285
Max Act: 6.4160. Min Act: -0.1700
Data Index: 447925 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7285. Min Range: -6.7285
Max Act: 6.4473. Min Act: -0.1700
Data Index: 4357271 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7285. Min Range: -6.7285
Max Act: 6.3848. Min Act: -0.1700
Data Index: 3698972 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7285. Min Range: -6.7285
Max Act: 6.3848. Min Act: -0.1700
Data Index: 1180093 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #19