Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4950 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8242. Min Range: -3.8242
Max Act: 3.8242. Min Act: -0.1700
Data Index: 1665577 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8242. Min Range: -3.8242
Max Act: 3.7930. Min Act: -0.1700
Data Index: 4734081 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8242. Min Range: -3.8242
Max Act: 3.6991. Min Act: -0.1700
Data Index: 5644038 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8242. Min Range: -3.8242
Max Act: 3.6052. Min Act: -0.1700
Data Index: 5791699 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8242. Min Range: -3.8242
Max Act: 3.5896. Min Act: -0.1700
Data Index: 7885657 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8242. Min Range: -3.8242
Max Act: 3.5896. Min Act: -0.1700
Data Index: 1463012 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8242. Min Range: -3.8242
Max Act: 3.5739. Min Act: -0.1700
Data Index: 516686 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8242. Min Range: -3.8242
Max Act: 3.5583. Min Act: -0.1700
Data Index: 8202547 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8242. Min Range: -3.8242
Max Act: 3.5426. Min Act: -0.1700
Data Index: 8762366 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8242. Min Range: -3.8242
Max Act: 3.5426. Min Act: -0.1700
Data Index: 5766658 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8242. Min Range: -3.8242
Max Act: 3.5426. Min Act: -0.1700
Data Index: 8197681 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8242. Min Range: -3.8242
Max Act: 3.5113. Min Act: -0.1700
Data Index: 5862441 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8242. Min Range: -3.8242
Max Act: 3.5113. Min Act: -0.1700
Data Index: 6919374 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8242. Min Range: -3.8242
Max Act: 3.5270. Min Act: -0.1700
Data Index: 2900261 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8242. Min Range: -3.8242
Max Act: 3.5113. Min Act: -0.1700
Data Index: 5877806 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8242. Min Range: -3.8242
Max Act: 3.4956. Min Act: -0.1700
Data Index: 1341673 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8242. Min Range: -3.8242
Max Act: 3.4956. Min Act: -0.1700
Data Index: 632535 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8242. Min Range: -3.8242
Max Act: 3.4643. Min Act: -0.1700
Data Index: 6829742 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8242. Min Range: -3.8242
Max Act: 3.4643. Min Act: -0.1700
Data Index: 8106194 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8242. Min Range: -3.8242
Max Act: 3.4643. Min Act: -0.1700
Data Index: 4367562 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #19