Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1390 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5702. Min Range: -6.5702
Max Act: 6.5702. Min Act: -0.1700
Data Index: 4118950 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5702. Min Range: -6.5702
Max Act: 6.3827. Min Act: -0.1700
Data Index: 4562321 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5702. Min Range: -6.5702
Max Act: 6.3202. Min Act: -0.1700
Data Index: 6233734 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5702. Min Range: -6.5702
Max Act: 6.2577. Min Act: -0.1700
Data Index: 7803903 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5702. Min Range: -6.5702
Max Act: 6.1952. Min Act: -0.1700
Data Index: 2068539 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5702. Min Range: -6.5702
Max Act: 6.2264. Min Act: -0.1700
Data Index: 5026710 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5702. Min Range: -6.5702
Max Act: 6.1639. Min Act: -0.1700
Data Index: 5057787 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5702. Min Range: -6.5702
Max Act: 6.1327. Min Act: -0.1700
Data Index: 3998698 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5702. Min Range: -6.5702
Max Act: 6.1014. Min Act: -0.1700
Data Index: 7663965 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5702. Min Range: -6.5702
Max Act: 6.0389. Min Act: -0.1700
Data Index: 6430454 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5702. Min Range: -6.5702
Max Act: 6.1014. Min Act: -0.1700
Data Index: 2466009 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5702. Min Range: -6.5702
Max Act: 6.0702. Min Act: -0.1700
Data Index: 153936 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5702. Min Range: -6.5702
Max Act: 6.0702. Min Act: -0.1700
Data Index: 5057785 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5702. Min Range: -6.5702
Max Act: 6.0077. Min Act: -0.1700
Data Index: 4616352 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5702. Min Range: -6.5702
Max Act: 5.9764. Min Act: -0.1700
Data Index: 4556621 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5702. Min Range: -6.5702
Max Act: 5.9452. Min Act: -0.1700
Data Index: 1311718 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5702. Min Range: -6.5702
Max Act: 5.9139. Min Act: -0.1700
Data Index: 2270978 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5702. Min Range: -6.5702
Max Act: 5.9452. Min Act: -0.1700
Data Index: 6607900 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5702. Min Range: -6.5702
Max Act: 5.9452. Min Act: -0.1700
Data Index: 2080687 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5702. Min Range: -6.5702
Max Act: 5.9139. Min Act: -0.1700
Data Index: 6704676 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #19