Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1097 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8469. Min Range: -8.8469
Max Act: 8.8469. Min Act: -0.1700
Data Index: 4885132 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8469. Min Range: -8.8469
Max Act: 8.7844. Min Act: -0.1700
Data Index: 6341209 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8469. Min Range: -8.8469
Max Act: 8.7219. Min Act: -0.1700
Data Index: 6689222 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8469. Min Range: -8.8469
Max Act: 8.7219. Min Act: -0.1700
Data Index: 5748087 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8469. Min Range: -8.8469
Max Act: 8.6594. Min Act: -0.1700
Data Index: 671140 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8469. Min Range: -8.8469
Max Act: 8.6594. Min Act: -0.1700
Data Index: 2963526 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8469. Min Range: -8.8469
Max Act: 8.5969. Min Act: -0.1700
Data Index: 1315728 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8469. Min Range: -8.8469
Max Act: 8.5969. Min Act: -0.1700
Data Index: 6720664 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8469. Min Range: -8.8469
Max Act: 8.5969. Min Act: -0.1700
Data Index: 2038693 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8469. Min Range: -8.8469
Max Act: 8.5344. Min Act: -0.1700
Data Index: 8775151 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8469. Min Range: -8.8469
Max Act: 8.5344. Min Act: -0.1700
Data Index: 3463795 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8469. Min Range: -8.8469
Max Act: 8.4719. Min Act: -0.1700
Data Index: 1048029 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8469. Min Range: -8.8469
Max Act: 8.4719. Min Act: -0.1700
Data Index: 1846434 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8469. Min Range: -8.8469
Max Act: 8.4094. Min Act: -0.1700
Data Index: 7165751 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8469. Min Range: -8.8469
Max Act: 8.3469. Min Act: -0.1700
Data Index: 410155 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8469. Min Range: -8.8469
Max Act: 8.3469. Min Act: -0.1700
Data Index: 6457481 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8469. Min Range: -8.8469
Max Act: 8.2844. Min Act: -0.1700
Data Index: 4512342 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8469. Min Range: -8.8469
Max Act: 8.2844. Min Act: -0.1700
Data Index: 524125 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8469. Min Range: -8.8469
Max Act: 8.2844. Min Act: -0.1700
Data Index: 7592087 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8469. Min Range: -8.8469
Max Act: 8.2844. Min Act: -0.1700
Data Index: 4416443 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #19