Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2804 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9563. Min Range: -5.9563
Max Act: 5.9563. Min Act: -0.1700
Data Index: 5544432 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9563. Min Range: -5.9563
Max Act: 5.8626. Min Act: -0.1700
Data Index: 1679832 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9563. Min Range: -5.9563
Max Act: 5.6751. Min Act: -0.1700
Data Index: 4160460 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9563. Min Range: -5.9563
Max Act: 5.5501. Min Act: -0.1700
Data Index: 7871258 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9563. Min Range: -5.9563
Max Act: 5.5501. Min Act: -0.1700
Data Index: 4200511 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9563. Min Range: -5.9563
Max Act: 5.5501. Min Act: -0.1700
Data Index: 7871263 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9563. Min Range: -5.9563
Max Act: 5.5501. Min Act: -0.1700
Data Index: 8557145 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9563. Min Range: -5.9563
Max Act: 5.5501. Min Act: -0.1700
Data Index: 948351 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9563. Min Range: -5.9563
Max Act: 5.5501. Min Act: -0.1700
Data Index: 162558 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9563. Min Range: -5.9563
Max Act: 5.4876. Min Act: -0.1700
Data Index: 7871248 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9563. Min Range: -5.9563
Max Act: 5.4876. Min Act: -0.1700
Data Index: 7635970 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9563. Min Range: -5.9563
Max Act: 5.4563. Min Act: -0.1700
Data Index: 1793787 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9563. Min Range: -5.9563
Max Act: 5.3938. Min Act: -0.1700
Data Index: 3091020 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9563. Min Range: -5.9563
Max Act: 5.4563. Min Act: -0.1700
Data Index: 4718658 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9563. Min Range: -5.9563
Max Act: 5.4251. Min Act: -0.1700
Data Index: 55450 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9563. Min Range: -5.9563
Max Act: 5.4251. Min Act: -0.1700
Data Index: 4042443 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9563. Min Range: -5.9563
Max Act: 5.4563. Min Act: -0.1700
Data Index: 7871246 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9563. Min Range: -5.9563
Max Act: 5.4251. Min Act: -0.1700
Data Index: 8751754 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9563. Min Range: -5.9563
Max Act: 5.3626. Min Act: -0.1700
Data Index: 4344331 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9563. Min Range: -5.9563
Max Act: 5.3626. Min Act: -0.1700
Data Index: 7871243 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #19