Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1449 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0901. Min Range: -3.0901
Max Act: 3.0901. Min Act: -0.1700
Data Index: 4053208 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0901. Min Range: -3.0901
Max Act: 3.0270. Min Act: -0.1700
Data Index: 1872505 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0901. Min Range: -3.0901
Max Act: 3.0112. Min Act: -0.1700
Data Index: 736588 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0901. Min Range: -3.0901
Max Act: 2.9796. Min Act: -0.1700
Data Index: 3003053 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0901. Min Range: -3.0901
Max Act: 2.9638. Min Act: -0.1700
Data Index: 5137301 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0901. Min Range: -3.0901
Max Act: 2.9321. Min Act: -0.1700
Data Index: 1481371 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0901. Min Range: -3.0901
Max Act: 2.9479. Min Act: -0.1700
Data Index: 782996 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0901. Min Range: -3.0901
Max Act: 2.9004. Min Act: -0.1700
Data Index: 696258 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0901. Min Range: -3.0901
Max Act: 2.8687. Min Act: -0.1700
Data Index: 1918501 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0901. Min Range: -3.0901
Max Act: 2.8845. Min Act: -0.1700
Data Index: 7986058 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0901. Min Range: -3.0901
Max Act: 2.8687. Min Act: -0.1700
Data Index: 1160046 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0901. Min Range: -3.0901
Max Act: 2.9004. Min Act: -0.1700
Data Index: 2819303 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0901. Min Range: -3.0901
Max Act: 2.8687. Min Act: -0.1700
Data Index: 1002704 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0901. Min Range: -3.0901
Max Act: 2.8528. Min Act: -0.1700
Data Index: 2187900 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0901. Min Range: -3.0901
Max Act: 2.8369. Min Act: -0.1700
Data Index: 233819 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0901. Min Range: -3.0901
Max Act: 2.8210. Min Act: -0.1700
Data Index: 3686978 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0901. Min Range: -3.0901
Max Act: 2.8369. Min Act: -0.1700
Data Index: 8313246 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0901. Min Range: -3.0901
Max Act: 2.8210. Min Act: -0.1700
Data Index: 8584972 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0901. Min Range: -3.0901
Max Act: 2.8369. Min Act: -0.1700
Data Index: 4285187 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0901. Min Range: -3.0901
Max Act: 2.8210. Min Act: -0.1700
Data Index: 5710811 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #19