Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5105 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.4597. Min Range: -8.4597
Max Act: 8.4597. Min Act: -0.1700
Data Index: 4244444 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4597. Min Range: -8.4597
Max Act: 8.2722. Min Act: -0.1700
Data Index: 5714846 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4597. Min Range: -8.4597
Max Act: 8.2097. Min Act: -0.1700
Data Index: 2663883 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4597. Min Range: -8.4597
Max Act: 8.2097. Min Act: -0.1700
Data Index: 912581 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4597. Min Range: -8.4597
Max Act: 8.1472. Min Act: -0.1700
Data Index: 612463 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4597. Min Range: -8.4597
Max Act: 8.2097. Min Act: -0.1700
Data Index: 5100638 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4597. Min Range: -8.4597
Max Act: 8.1472. Min Act: -0.1700
Data Index: 4336297 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4597. Min Range: -8.4597
Max Act: 8.1472. Min Act: -0.1700
Data Index: 1899856 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4597. Min Range: -8.4597
Max Act: 8.0847. Min Act: -0.1700
Data Index: 2779719 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4597. Min Range: -8.4597
Max Act: 8.0847. Min Act: -0.1700
Data Index: 3180149 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4597. Min Range: -8.4597
Max Act: 8.0222. Min Act: -0.1700
Data Index: 1172086 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4597. Min Range: -8.4597
Max Act: 8.0222. Min Act: -0.1700
Data Index: 578686 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4597. Min Range: -8.4597
Max Act: 7.9597. Min Act: -0.1700
Data Index: 1043834 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4597. Min Range: -8.4597
Max Act: 7.9597. Min Act: -0.1700
Data Index: 5652032 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4597. Min Range: -8.4597
Max Act: 8.0222. Min Act: -0.1700
Data Index: 367621 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4597. Min Range: -8.4597
Max Act: 7.8972. Min Act: -0.1700
Data Index: 3947855 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4597. Min Range: -8.4597
Max Act: 7.8972. Min Act: -0.1700
Data Index: 1022042 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4597. Min Range: -8.4597
Max Act: 7.8972. Min Act: -0.1700
Data Index: 949335 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4597. Min Range: -8.4597
Max Act: 7.8972. Min Act: -0.1700
Data Index: 8781120 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4597. Min Range: -8.4597
Max Act: 7.8972. Min Act: -0.1700
Data Index: 1972810 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #19