Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4629 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7213. Min Range: -6.7213
Max Act: 6.7213. Min Act: -0.1700
Data Index: 7337336 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7213. Min Range: -6.7213
Max Act: 6.4713. Min Act: -0.1700
Data Index: 8715648 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7213. Min Range: -6.7213
Max Act: 6.3776. Min Act: -0.1700
Data Index: 7310294 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7213. Min Range: -6.7213
Max Act: 6.3776. Min Act: -0.1700
Data Index: 4996825 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7213. Min Range: -6.7213
Max Act: 6.3151. Min Act: -0.1700
Data Index: 9649 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7213. Min Range: -6.7213
Max Act: 6.0963. Min Act: -0.1700
Data Index: 5896985 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7213. Min Range: -6.7213
Max Act: 6.0963. Min Act: -0.1700
Data Index: 2901946 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7213. Min Range: -6.7213
Max Act: 6.0338. Min Act: -0.1700
Data Index: 8545991 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7213. Min Range: -6.7213
Max Act: 6.0338. Min Act: -0.1700
Data Index: 63918 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7213. Min Range: -6.7213
Max Act: 6.0026. Min Act: -0.1700
Data Index: 1789748 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7213. Min Range: -6.7213
Max Act: 5.9401. Min Act: -0.1700
Data Index: 4502001 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7213. Min Range: -6.7213
Max Act: 5.9713. Min Act: -0.1700
Data Index: 3467100 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7213. Min Range: -6.7213
Max Act: 5.9713. Min Act: -0.1700
Data Index: 5932408 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7213. Min Range: -6.7213
Max Act: 5.9713. Min Act: -0.1700
Data Index: 2724897 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7213. Min Range: -6.7213
Max Act: 5.9088. Min Act: -0.1700
Data Index: 7811281 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7213. Min Range: -6.7213
Max Act: 5.9088. Min Act: -0.1700
Data Index: 2186014 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7213. Min Range: -6.7213
Max Act: 5.8776. Min Act: -0.1700
Data Index: 2461712 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7213. Min Range: -6.7213
Max Act: 5.8776. Min Act: -0.1700
Data Index: 5915158 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7213. Min Range: -6.7213
Max Act: 5.8463. Min Act: -0.1700
Data Index: 925174 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7213. Min Range: -6.7213
Max Act: 5.8151. Min Act: -0.1700
Data Index: 7808261 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #19