Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3601 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5400. Min Range: -5.5400
Max Act: 5.5400. Min Act: -0.1700
Data Index: 5595712 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5400. Min Range: -5.5400
Max Act: 5.3838. Min Act: -0.1700
Data Index: 1443204 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5400. Min Range: -5.5400
Max Act: 5.4463. Min Act: -0.1700
Data Index: 64054 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5400. Min Range: -5.5400
Max Act: 5.3213. Min Act: -0.1700
Data Index: 605232 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5400. Min Range: -5.5400
Max Act: 5.2900. Min Act: -0.1700
Data Index: 297698 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5400. Min Range: -5.5400
Max Act: 5.2588. Min Act: -0.1700
Data Index: 7358564 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5400. Min Range: -5.5400
Max Act: 5.2275. Min Act: -0.1700
Data Index: 2577727 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5400. Min Range: -5.5400
Max Act: 5.2275. Min Act: -0.1700
Data Index: 4616365 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5400. Min Range: -5.5400
Max Act: 5.2275. Min Act: -0.1700
Data Index: 3831857 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5400. Min Range: -5.5400
Max Act: 5.1963. Min Act: -0.1700
Data Index: 87001 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5400. Min Range: -5.5400
Max Act: 5.1963. Min Act: -0.1700
Data Index: 2986585 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5400. Min Range: -5.5400
Max Act: 5.1963. Min Act: -0.1700
Data Index: 8753083 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5400. Min Range: -5.5400
Max Act: 5.1650. Min Act: -0.1700
Data Index: 4382880 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5400. Min Range: -5.5400
Max Act: 5.1338. Min Act: -0.1700
Data Index: 8078648 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5400. Min Range: -5.5400
Max Act: 5.1025. Min Act: -0.1700
Data Index: 7592080 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5400. Min Range: -5.5400
Max Act: 5.1025. Min Act: -0.1700
Data Index: 6661658 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5400. Min Range: -5.5400
Max Act: 5.0400. Min Act: -0.1700
Data Index: 5280535 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5400. Min Range: -5.5400
Max Act: 5.1025. Min Act: -0.1700
Data Index: 3332229 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5400. Min Range: -5.5400
Max Act: 5.0713. Min Act: -0.1700
Data Index: 2066999 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5400. Min Range: -5.5400
Max Act: 5.0400. Min Act: -0.1700
Data Index: 4839012 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #19