Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4582 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5067. Min Range: -6.5067
Max Act: 6.5067. Min Act: -0.1700
Data Index: 7166313 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5067. Min Range: -6.5067
Max Act: 6.1629. Min Act: -0.1700
Data Index: 8686010 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5067. Min Range: -6.5067
Max Act: 5.9442. Min Act: -0.1700
Data Index: 3628847 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5067. Min Range: -6.5067
Max Act: 5.8817. Min Act: -0.1700
Data Index: 8804475 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5067. Min Range: -6.5067
Max Act: 5.8504. Min Act: -0.1700
Data Index: 1885749 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5067. Min Range: -6.5067
Max Act: 5.7567. Min Act: -0.1700
Data Index: 8484105 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5067. Min Range: -6.5067
Max Act: 5.7254. Min Act: -0.1700
Data Index: 7930710 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5067. Min Range: -6.5067
Max Act: 5.6629. Min Act: -0.1700
Data Index: 5864072 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5067. Min Range: -6.5067
Max Act: 5.6629. Min Act: -0.1700
Data Index: 6780560 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5067. Min Range: -6.5067
Max Act: 5.6317. Min Act: -0.1700
Data Index: 4552310 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5067. Min Range: -6.5067
Max Act: 5.6004. Min Act: -0.1700
Data Index: 3812476 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5067. Min Range: -6.5067
Max Act: 5.6004. Min Act: -0.1700
Data Index: 1208865 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5067. Min Range: -6.5067
Max Act: 5.6004. Min Act: -0.1700
Data Index: 8104281 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5067. Min Range: -6.5067
Max Act: 5.5692. Min Act: -0.1700
Data Index: 3894891 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5067. Min Range: -6.5067
Max Act: 5.5692. Min Act: -0.1700
Data Index: 678556 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5067. Min Range: -6.5067
Max Act: 5.5379. Min Act: -0.1700
Data Index: 6533723 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5067. Min Range: -6.5067
Max Act: 5.5067. Min Act: -0.1700
Data Index: 7218729 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5067. Min Range: -6.5067
Max Act: 5.5692. Min Act: -0.1700
Data Index: 2941270 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5067. Min Range: -6.5067
Max Act: 5.5379. Min Act: -0.1700
Data Index: 1484831 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5067. Min Range: -6.5067
Max Act: 5.5692. Min Act: -0.1700
Data Index: 6037708 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #19