Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 462 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7692. Min Range: -5.7692
Max Act: 5.7692. Min Act: -0.1700
Data Index: 1224453 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7692. Min Range: -5.7692
Max Act: 5.5504. Min Act: -0.1700
Data Index: 4088005 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7692. Min Range: -5.7692
Max Act: 5.4567. Min Act: -0.1700
Data Index: 7511047 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7692. Min Range: -5.7692
Max Act: 5.4254. Min Act: -0.1700
Data Index: 4121918 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7692. Min Range: -5.7692
Max Act: 5.3942. Min Act: -0.1700
Data Index: 5522541 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7692. Min Range: -5.7692
Max Act: 5.3942. Min Act: -0.1700
Data Index: 2065901 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7692. Min Range: -5.7692
Max Act: 5.3942. Min Act: -0.1700
Data Index: 5750034 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7692. Min Range: -5.7692
Max Act: 5.3942. Min Act: -0.1700
Data Index: 5748719 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7692. Min Range: -5.7692
Max Act: 5.3317. Min Act: -0.1700
Data Index: 3088472 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7692. Min Range: -5.7692
Max Act: 5.3629. Min Act: -0.1700
Data Index: 4121914 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7692. Min Range: -5.7692
Max Act: 5.3629. Min Act: -0.1699
Data Index: 3750452 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7692. Min Range: -5.7692
Max Act: 5.3629. Min Act: -0.1700
Data Index: 3965126 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7692. Min Range: -5.7692
Max Act: 5.3629. Min Act: -0.1700
Data Index: 7949548 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7692. Min Range: -5.7692
Max Act: 5.3629. Min Act: -0.1700
Data Index: 1925665 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7692. Min Range: -5.7692
Max Act: 5.3629. Min Act: -0.1700
Data Index: 8559266 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7692. Min Range: -5.7692
Max Act: 5.3629. Min Act: -0.1700
Data Index: 302996 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7692. Min Range: -5.7692
Max Act: 5.3629. Min Act: -0.1700
Data Index: 8024503 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7692. Min Range: -5.7692
Max Act: 5.3629. Min Act: -0.1700
Data Index: 4121909 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7692. Min Range: -5.7692
Max Act: 5.3317. Min Act: -0.1700
Data Index: 7836890 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7692. Min Range: -5.7692
Max Act: 5.3317. Min Act: -0.1700
Data Index: 1327447 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #19