Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3012 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.1779. Min Range: -7.1779
Max Act: 7.1779. Min Act: -0.1700
Data Index: 2717047 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1779. Min Range: -7.1779
Max Act: 7.0842. Min Act: -0.1700
Data Index: 1892242 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1779. Min Range: -7.1779
Max Act: 7.0529. Min Act: -0.1700
Data Index: 3339206 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1779. Min Range: -7.1779
Max Act: 7.0529. Min Act: -0.1700
Data Index: 198841 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1779. Min Range: -7.1779
Max Act: 7.0217. Min Act: -0.1700
Data Index: 1114623 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1779. Min Range: -7.1779
Max Act: 6.9904. Min Act: -0.1700
Data Index: 6900593 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1779. Min Range: -7.1779
Max Act: 6.8967. Min Act: -0.1700
Data Index: 3840922 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1779. Min Range: -7.1779
Max Act: 6.8967. Min Act: -0.1700
Data Index: 5398967 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1779. Min Range: -7.1779
Max Act: 6.8654. Min Act: -0.1700
Data Index: 511922 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1779. Min Range: -7.1779
Max Act: 6.8967. Min Act: -0.1700
Data Index: 6626096 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1779. Min Range: -7.1779
Max Act: 6.8029. Min Act: -0.1700
Data Index: 8232499 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1779. Min Range: -7.1779
Max Act: 6.8029. Min Act: -0.1700
Data Index: 6511824 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1779. Min Range: -7.1779
Max Act: 6.8029. Min Act: -0.1700
Data Index: 7536710 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1779. Min Range: -7.1779
Max Act: 6.8029. Min Act: -0.1700
Data Index: 8362386 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1779. Min Range: -7.1779
Max Act: 6.8029. Min Act: -0.1700
Data Index: 1325953 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1779. Min Range: -7.1779
Max Act: 6.7717. Min Act: -0.1700
Data Index: 787780 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1779. Min Range: -7.1779
Max Act: 6.8029. Min Act: -0.1700
Data Index: 6823246 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1779. Min Range: -7.1779
Max Act: 6.8029. Min Act: -0.1700
Data Index: 4142236 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1779. Min Range: -7.1779
Max Act: 6.8029. Min Act: -0.1700
Data Index: 7970938 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1779. Min Range: -7.1779
Max Act: 6.7404. Min Act: -0.1700
Data Index: 5228264 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #19