Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4050 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.0855. Min Range: -8.0855
Max Act: 8.0855. Min Act: -0.1700
Data Index: 2187853 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0855. Min Range: -8.0855
Max Act: 8.0855. Min Act: -0.1700
Data Index: 6658682 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0855. Min Range: -8.0855
Max Act: 8.0230. Min Act: -0.1700
Data Index: 8050367 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0855. Min Range: -8.0855
Max Act: 7.7730. Min Act: -0.1700
Data Index: 6870603 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0855. Min Range: -8.0855
Max Act: 7.7105. Min Act: -0.1700
Data Index: 3301008 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0855. Min Range: -8.0855
Max Act: 7.6480. Min Act: -0.1700
Data Index: 4441851 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0855. Min Range: -8.0855
Max Act: 7.5855. Min Act: -0.1700
Data Index: 7974298 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0855. Min Range: -8.0855
Max Act: 7.6480. Min Act: -0.1700
Data Index: 4540866 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0855. Min Range: -8.0855
Max Act: 7.6480. Min Act: -0.1700
Data Index: 863452 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0855. Min Range: -8.0855
Max Act: 7.6480. Min Act: -0.1700
Data Index: 8677575 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0855. Min Range: -8.0855
Max Act: 7.5543. Min Act: -0.1700
Data Index: 864832 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0855. Min Range: -8.0855
Max Act: 7.5543. Min Act: -0.1700
Data Index: 8199702 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0855. Min Range: -8.0855
Max Act: 7.4293. Min Act: -0.1700
Data Index: 388456 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0855. Min Range: -8.0855
Max Act: 7.5230. Min Act: -0.1700
Data Index: 1857983 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0855. Min Range: -8.0855
Max Act: 7.5230. Min Act: -0.1700
Data Index: 1480974 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0855. Min Range: -8.0855
Max Act: 7.5230. Min Act: -0.1700
Data Index: 8060712 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0855. Min Range: -8.0855
Max Act: 7.4293. Min Act: -0.1700
Data Index: 897927 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0855. Min Range: -8.0855
Max Act: 7.4918. Min Act: -0.1700
Data Index: 7885584 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0855. Min Range: -8.0855
Max Act: 7.4918. Min Act: -0.1700
Data Index: 1987834 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0855. Min Range: -8.0855
Max Act: 7.4918. Min Act: -0.1700
Data Index: 2133850 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #19