Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4225 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6462. Min Range: -6.6462
Max Act: 6.6462. Min Act: -0.1700
Data Index: 5022791 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6462. Min Range: -6.6462
Max Act: 6.2087. Min Act: -0.1700
Data Index: 1499963 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6462. Min Range: -6.6462
Max Act: 6.2087. Min Act: -0.1700
Data Index: 2834747 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6462. Min Range: -6.6462
Max Act: 6.1462. Min Act: -0.1700
Data Index: 600191 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6462. Min Range: -6.6462
Max Act: 6.1149. Min Act: -0.1700
Data Index: 8222457 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6462. Min Range: -6.6462
Max Act: 6.0837. Min Act: -0.1700
Data Index: 2102055 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6462. Min Range: -6.6462
Max Act: 6.0837. Min Act: -0.1700
Data Index: 3887323 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6462. Min Range: -6.6462
Max Act: 6.0524. Min Act: -0.1700
Data Index: 6839978 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6462. Min Range: -6.6462
Max Act: 6.0212. Min Act: -0.1676
Data Index: 7765410 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6462. Min Range: -6.6462
Max Act: 6.0212. Min Act: -0.1700
Data Index: 2442835 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6462. Min Range: -6.6462
Max Act: 5.9899. Min Act: -0.1700
Data Index: 1937372 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6462. Min Range: -6.6462
Max Act: 6.0212. Min Act: -0.1700
Data Index: 2527808 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6462. Min Range: -6.6462
Max Act: 5.9899. Min Act: -0.1698
Data Index: 7584487 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6462. Min Range: -6.6462
Max Act: 5.9899. Min Act: -0.1700
Data Index: 508794 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6462. Min Range: -6.6462
Max Act: 5.9587. Min Act: -0.1700
Data Index: 1190755 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6462. Min Range: -6.6462
Max Act: 5.9587. Min Act: -0.1698
Data Index: 2342412 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6462. Min Range: -6.6462
Max Act: 5.9899. Min Act: -0.1700
Data Index: 4761950 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6462. Min Range: -6.6462
Max Act: 5.9587. Min Act: -0.1680
Data Index: 5577820 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6462. Min Range: -6.6462
Max Act: 5.9587. Min Act: -0.1699
Data Index: 1831810 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6462. Min Range: -6.6462
Max Act: 5.9274. Min Act: -0.1700
Data Index: 3286437 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #19