Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3797 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1067. Min Range: -3.1067
Max Act: 3.1067. Min Act: -0.1700
Data Index: 324420 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1067. Min Range: -3.1067
Max Act: 3.0752. Min Act: -0.1700
Data Index: 7139681 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1067. Min Range: -3.1067
Max Act: 3.0436. Min Act: -0.1700
Data Index: 1146843 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1067. Min Range: -3.1067
Max Act: 3.0278. Min Act: -0.1700
Data Index: 8703014 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1067. Min Range: -3.1067
Max Act: 3.0436. Min Act: -0.1700
Data Index: 5720337 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1067. Min Range: -3.1067
Max Act: 3.0120. Min Act: -0.1700
Data Index: 1423328 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1067. Min Range: -3.1067
Max Act: 3.0278. Min Act: -0.1700
Data Index: 2045643 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1067. Min Range: -3.1067
Max Act: 3.0278. Min Act: -0.1700
Data Index: 8229121 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1067. Min Range: -3.1067
Max Act: 3.0278. Min Act: -0.1700
Data Index: 304714 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1067. Min Range: -3.1067
Max Act: 2.9962. Min Act: -0.1700
Data Index: 8717626 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1067. Min Range: -3.1067
Max Act: 2.9962. Min Act: -0.1700
Data Index: 6408711 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1067. Min Range: -3.1067
Max Act: 2.9962. Min Act: -0.1700
Data Index: 6419649 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1067. Min Range: -3.1067
Max Act: 2.9962. Min Act: -0.1700
Data Index: 6179785 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1067. Min Range: -3.1067
Max Act: 2.9804. Min Act: -0.1700
Data Index: 4490812 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1067. Min Range: -3.1067
Max Act: 2.9804. Min Act: -0.1700
Data Index: 2230009 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1067. Min Range: -3.1067
Max Act: 2.9962. Min Act: -0.1700
Data Index: 2494471 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1067. Min Range: -3.1067
Max Act: 3.0120. Min Act: -0.1700
Data Index: 4620496 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1067. Min Range: -3.1067
Max Act: 2.9804. Min Act: -0.1700
Data Index: 2436285 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1067. Min Range: -3.1067
Max Act: 2.9962. Min Act: -0.1700
Data Index: 7401937 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1067. Min Range: -3.1067
Max Act: 2.9804. Min Act: -0.1700
Data Index: 2953794 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #19