Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 68 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8487. Min Range: -3.8487
Max Act: 3.8487. Min Act: -0.1700
Data Index: 6563529 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8487. Min Range: -3.8487
Max Act: 3.7549. Min Act: -0.1700
Data Index: 4839216 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8487. Min Range: -3.8487
Max Act: 3.6297. Min Act: -0.1700
Data Index: 4905846 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8487. Min Range: -3.8487
Max Act: 3.6297. Min Act: -0.1700
Data Index: 6935163 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8487. Min Range: -3.8487
Max Act: 3.6297. Min Act: -0.1700
Data Index: 1865568 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8487. Min Range: -3.8487
Max Act: 3.6297. Min Act: -0.1700
Data Index: 7881174 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8487. Min Range: -3.8487
Max Act: 3.6297. Min Act: -0.1700
Data Index: 58253 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8487. Min Range: -3.8487
Max Act: 3.5984. Min Act: -0.1700
Data Index: 7302673 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8487. Min Range: -3.8487
Max Act: 3.5984. Min Act: -0.1700
Data Index: 7699661 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8487. Min Range: -3.8487
Max Act: 3.5671. Min Act: -0.1700
Data Index: 1018794 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8487. Min Range: -3.8487
Max Act: 3.5984. Min Act: -0.1700
Data Index: 4034899 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8487. Min Range: -3.8487
Max Act: 3.5358. Min Act: -0.1700
Data Index: 6379979 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8487. Min Range: -3.8487
Max Act: 3.5671. Min Act: -0.1700
Data Index: 8144005 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8487. Min Range: -3.8487
Max Act: 3.5045. Min Act: -0.1700
Data Index: 5445496 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8487. Min Range: -3.8487
Max Act: 3.5045. Min Act: -0.1700
Data Index: 3725461 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8487. Min Range: -3.8487
Max Act: 3.5045. Min Act: -0.1700
Data Index: 1293725 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8487. Min Range: -3.8487
Max Act: 3.5045. Min Act: -0.1700
Data Index: 7696911 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8487. Min Range: -3.8487
Max Act: 3.5045. Min Act: -0.1700
Data Index: 3180850 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8487. Min Range: -3.8487
Max Act: 3.5045. Min Act: -0.1700
Data Index: 5356877 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8487. Min Range: -3.8487
Max Act: 3.5045. Min Act: -0.1700
Data Index: 5060349 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #19