Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2672 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3260. Min Range: -5.3260
Max Act: 5.3260. Min Act: -0.1700
Data Index: 7566844 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3260. Min Range: -5.3260
Max Act: 5.3260. Min Act: -0.1700
Data Index: 7654021 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3260. Min Range: -5.3260
Max Act: 5.2948. Min Act: -0.1700
Data Index: 2312140 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3260. Min Range: -5.3260
Max Act: 5.2948. Min Act: -0.1700
Data Index: 8259367 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3260. Min Range: -5.3260
Max Act: 5.2635. Min Act: -0.1700
Data Index: 8752422 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3260. Min Range: -5.3260
Max Act: 5.2948. Min Act: -0.1700
Data Index: 2226445 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3260. Min Range: -5.3260
Max Act: 5.2323. Min Act: -0.1700
Data Index: 5730499 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3260. Min Range: -5.3260
Max Act: 5.2323. Min Act: -0.1700
Data Index: 6623231 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3260. Min Range: -5.3260
Max Act: 5.2010. Min Act: -0.1700
Data Index: 74581 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3260. Min Range: -5.3260
Max Act: 5.2323. Min Act: -0.1700
Data Index: 1943552 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3260. Min Range: -5.3260
Max Act: 5.2010. Min Act: -0.1700
Data Index: 2243805 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3260. Min Range: -5.3260
Max Act: 5.1698. Min Act: -0.1700
Data Index: 6005909 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3260. Min Range: -5.3260
Max Act: 5.1698. Min Act: -0.1700
Data Index: 789273 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3260. Min Range: -5.3260
Max Act: 5.1385. Min Act: -0.1700
Data Index: 3196506 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3260. Min Range: -5.3260
Max Act: 5.2010. Min Act: -0.1700
Data Index: 8478621 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3260. Min Range: -5.3260
Max Act: 5.1698. Min Act: -0.1700
Data Index: 2422607 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3260. Min Range: -5.3260
Max Act: 5.1698. Min Act: -0.1700
Data Index: 8456161 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3260. Min Range: -5.3260
Max Act: 5.1698. Min Act: -0.1700
Data Index: 3214253 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3260. Min Range: -5.3260
Max Act: 5.1698. Min Act: -0.1700
Data Index: 4407900 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3260. Min Range: -5.3260
Max Act: 5.1698. Min Act: -0.1700
Data Index: 220042 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #19