Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1339 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2598. Min Range: -5.2598
Max Act: 5.2598. Min Act: -0.1700
Data Index: 4825997 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2598. Min Range: -5.2598
Max Act: 5.2285. Min Act: -0.1700
Data Index: 390666 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2598. Min Range: -5.2598
Max Act: 5.0410. Min Act: -0.1700
Data Index: 7864796 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2598. Min Range: -5.2598
Max Act: 5.0410. Min Act: -0.1700
Data Index: 7516732 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2598. Min Range: -5.2598
Max Act: 5.0723. Min Act: -0.1700
Data Index: 6321675 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2598. Min Range: -5.2598
Max Act: 5.0098. Min Act: -0.1700
Data Index: 4582699 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2598. Min Range: -5.2598
Max Act: 5.0410. Min Act: -0.1700
Data Index: 4441662 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2598. Min Range: -5.2598
Max Act: 5.0410. Min Act: -0.1700
Data Index: 1104335 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2598. Min Range: -5.2598
Max Act: 5.0098. Min Act: -0.1700
Data Index: 5260338 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2598. Min Range: -5.2598
Max Act: 5.0098. Min Act: -0.1700
Data Index: 175939 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2598. Min Range: -5.2598
Max Act: 4.9785. Min Act: -0.1700
Data Index: 3999534 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2598. Min Range: -5.2598
Max Act: 5.0410. Min Act: -0.1700
Data Index: 186835 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2598. Min Range: -5.2598
Max Act: 5.0098. Min Act: -0.1700
Data Index: 3574283 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2598. Min Range: -5.2598
Max Act: 4.9473. Min Act: -0.1700
Data Index: 4121188 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2598. Min Range: -5.2598
Max Act: 4.9473. Min Act: -0.1700
Data Index: 5057855 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2598. Min Range: -5.2598
Max Act: 5.0098. Min Act: -0.1700
Data Index: 7421375 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2598. Min Range: -5.2598
Max Act: 4.9473. Min Act: -0.1700
Data Index: 6680319 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2598. Min Range: -5.2598
Max Act: 4.9785. Min Act: -0.1700
Data Index: 5863975 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2598. Min Range: -5.2598
Max Act: 4.9785. Min Act: -0.1700
Data Index: 2014966 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2598. Min Range: -5.2598
Max Act: 4.9160. Min Act: -0.1700
Data Index: 3102632 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #19