Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5551 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9180. Min Range: -6.9180
Max Act: 6.8868. Min Act: -0.1700
Data Index: 3382829 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9180. Min Range: -6.9180
Max Act: 6.9180. Min Act: -0.1700
Data Index: 3644484 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9180. Min Range: -6.9180
Max Act: 6.7305. Min Act: -0.1700
Data Index: 1404555 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9180. Min Range: -6.9180
Max Act: 6.6680. Min Act: -0.1700
Data Index: 5482451 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9180. Min Range: -6.9180
Max Act: 6.6055. Min Act: -0.1700
Data Index: 5386252 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9180. Min Range: -6.9180
Max Act: 6.5743. Min Act: -0.1700
Data Index: 1909512 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9180. Min Range: -6.9180
Max Act: 6.5743. Min Act: -0.1700
Data Index: 4407221 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9180. Min Range: -6.9180
Max Act: 6.5118. Min Act: -0.1700
Data Index: 5928507 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9180. Min Range: -6.9180
Max Act: 6.5118. Min Act: -0.1700
Data Index: 2631388 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9180. Min Range: -6.9180
Max Act: 6.5118. Min Act: -0.1700
Data Index: 5729944 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9180. Min Range: -6.9180
Max Act: 6.4805. Min Act: -0.1700
Data Index: 1583169 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9180. Min Range: -6.9180
Max Act: 6.4493. Min Act: -0.1700
Data Index: 8445423 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9180. Min Range: -6.9180
Max Act: 6.4493. Min Act: -0.1700
Data Index: 3902522 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9180. Min Range: -6.9180
Max Act: 6.4493. Min Act: -0.1700
Data Index: 821351 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9180. Min Range: -6.9180
Max Act: 6.4493. Min Act: -0.1700
Data Index: 7384290 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9180. Min Range: -6.9180
Max Act: 6.4180. Min Act: -0.1700
Data Index: 6328994 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9180. Min Range: -6.9180
Max Act: 6.3868. Min Act: -0.1700
Data Index: 7236645 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9180. Min Range: -6.9180
Max Act: 6.4180. Min Act: -0.1700
Data Index: 2581666 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9180. Min Range: -6.9180
Max Act: 6.3868. Min Act: -0.1700
Data Index: 7258728 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9180. Min Range: -6.9180
Max Act: 6.3868. Min Act: -0.1700
Data Index: 7621872 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #19