Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3450 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6008. Min Range: -4.6008
Max Act: 4.6008. Min Act: -0.1700
Data Index: 2024303 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6008. Min Range: -4.6008
Max Act: 4.5696. Min Act: -0.1700
Data Index: 2710361 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6008. Min Range: -4.6008
Max Act: 4.5071. Min Act: -0.1700
Data Index: 5095669 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6008. Min Range: -4.6008
Max Act: 4.5383. Min Act: -0.1700
Data Index: 6969406 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6008. Min Range: -4.6008
Max Act: 4.4446. Min Act: -0.1700
Data Index: 611049 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6008. Min Range: -4.6008
Max Act: 4.4758. Min Act: -0.1700
Data Index: 2299966 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6008. Min Range: -4.6008
Max Act: 4.4758. Min Act: -0.1700
Data Index: 4712208 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6008. Min Range: -4.6008
Max Act: 4.4758. Min Act: -0.1700
Data Index: 5407543 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6008. Min Range: -4.6008
Max Act: 4.4446. Min Act: -0.1700
Data Index: 7279656 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6008. Min Range: -4.6008
Max Act: 4.4446. Min Act: -0.1700
Data Index: 2330016 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6008. Min Range: -4.6008
Max Act: 4.4446. Min Act: -0.1700
Data Index: 1676659 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6008. Min Range: -4.6008
Max Act: 4.4133. Min Act: -0.1700
Data Index: 8811338 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6008. Min Range: -4.6008
Max Act: 4.4133. Min Act: -0.1700
Data Index: 867104 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6008. Min Range: -4.6008
Max Act: 4.4133. Min Act: -0.1700
Data Index: 5021257 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6008. Min Range: -4.6008
Max Act: 4.4133. Min Act: -0.1700
Data Index: 2574583 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6008. Min Range: -4.6008
Max Act: 4.4133. Min Act: -0.1700
Data Index: 5947910 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6008. Min Range: -4.6008
Max Act: 4.4133. Min Act: -0.1700
Data Index: 7755890 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6008. Min Range: -4.6008
Max Act: 4.4446. Min Act: -0.1700
Data Index: 2316957 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6008. Min Range: -4.6008
Max Act: 4.4133. Min Act: -0.1700
Data Index: 6321361 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6008. Min Range: -4.6008
Max Act: 4.3508. Min Act: -0.1700
Data Index: 1208550 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #19