Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4307 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0578. Min Range: -5.0578
Max Act: 5.0578. Min Act: -0.1700
Data Index: 6288696 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0578. Min Range: -5.0578
Max Act: 4.7453. Min Act: -0.1700
Data Index: 5370293 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0578. Min Range: -5.0578
Max Act: 4.7140. Min Act: -0.1700
Data Index: 7254608 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0578. Min Range: -5.0578
Max Act: 4.6203. Min Act: -0.1700
Data Index: 4051371 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0578. Min Range: -5.0578
Max Act: 4.6515. Min Act: -0.1700
Data Index: 3763354 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0578. Min Range: -5.0578
Max Act: 4.5578. Min Act: -0.1700
Data Index: 2537271 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0578. Min Range: -5.0578
Max Act: 4.5578. Min Act: -0.1700
Data Index: 3032975 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0578. Min Range: -5.0578
Max Act: 4.5265. Min Act: -0.1700
Data Index: 6734292 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0578. Min Range: -5.0578
Max Act: 4.5265. Min Act: -0.1700
Data Index: 3513703 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0578. Min Range: -5.0578
Max Act: 4.4953. Min Act: -0.1700
Data Index: 4835490 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0578. Min Range: -5.0578
Max Act: 4.4640. Min Act: -0.1700
Data Index: 2007518 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0578. Min Range: -5.0578
Max Act: 4.4953. Min Act: -0.1700
Data Index: 1275862 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0578. Min Range: -5.0578
Max Act: 4.4640. Min Act: -0.1700
Data Index: 560039 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0578. Min Range: -5.0578
Max Act: 4.4640. Min Act: -0.1700
Data Index: 1095308 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0578. Min Range: -5.0578
Max Act: 4.4640. Min Act: -0.1700
Data Index: 1505088 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0578. Min Range: -5.0578
Max Act: 4.4640. Min Act: -0.1700
Data Index: 7509166 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0578. Min Range: -5.0578
Max Act: 4.4640. Min Act: -0.1700
Data Index: 2537270 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0578. Min Range: -5.0578
Max Act: 4.4640. Min Act: -0.1700
Data Index: 930207 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0578. Min Range: -5.0578
Max Act: 4.4328. Min Act: -0.1700
Data Index: 3749350 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0578. Min Range: -5.0578
Max Act: 4.4640. Min Act: -0.1700
Data Index: 6930663 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #19