Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 258 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.9868. Min Act: -0.1700
Data Index: 3989907 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.6743. Min Act: -0.1700
Data Index: 3529387 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.6743. Min Act: -0.1700
Data Index: 710219 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.6743. Min Act: -0.1700
Data Index: 7853457 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.6431. Min Act: -0.1700
Data Index: 4170269 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.6431. Min Act: -0.1700
Data Index: 4754858 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.5806. Min Act: -0.1700
Data Index: 6404875 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.6118. Min Act: -0.1700
Data Index: 2692691 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.6118. Min Act: -0.1700
Data Index: 936403 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.5806. Min Act: -0.1700
Data Index: 8071943 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.5806. Min Act: -0.1700
Data Index: 7302264 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.5493. Min Act: -0.1700
Data Index: 8159414 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.5181. Min Act: -0.1700
Data Index: 1835156 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.5181. Min Act: -0.1700
Data Index: 355656 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.5181. Min Act: -0.1700
Data Index: 5064887 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.5181. Min Act: -0.1700
Data Index: 7837650 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.5181. Min Act: -0.1700
Data Index: 78246 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.4868. Min Act: -0.1700
Data Index: 2562374 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.5181. Min Act: -0.1700
Data Index: 927304 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.4556. Min Act: -0.1700
Data Index: 3249004 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #19