Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2000 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 6.4828. Min Range: -6.4828
Max Act: 6.4828. Min Act: -0.1700
Data Index: 138927 (C4 (Web Text))
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4828. Min Range: -6.4828
Max Act: 6.2641. Min Act: -0.1700
Data Index: 1287514 (C4 (Web Text))
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4828. Min Range: -6.4828
Max Act: 6.2641. Min Act: -0.1700
Data Index: 186949 (C4 (Web Text))
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4828. Min Range: -6.4828
Max Act: 6.2328. Min Act: -0.1700
Data Index: 1008223 (C4 (Web Text))
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4828. Min Range: -6.4828
Max Act: 6.1703. Min Act: -0.1700
Data Index: 609418 (C4 (Web Text))
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4828. Min Range: -6.4828
Max Act: 6.2328. Min Act: -0.1700
Data Index: 814568 (C4 (Web Text))
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4828. Min Range: -6.4828
Max Act: 6.2328. Min Act: -0.1700
Data Index: 1333185 (C4 (Web Text))
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4828. Min Range: -6.4828
Max Act: 6.1703. Min Act: -0.1700
Data Index: 1134797 (C4 (Web Text))
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4828. Min Range: -6.4828
Max Act: 6.2016. Min Act: -0.1700
Data Index: 843342 (C4 (Web Text))
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4828. Min Range: -6.4828
Max Act: 6.2016. Min Act: -0.1700
Data Index: 427605 (C4 (Web Text))
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4828. Min Range: -6.4828
Max Act: 6.1703. Min Act: -0.1700
Data Index: 825165 (C4 (Web Text))
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4828. Min Range: -6.4828
Max Act: 6.1078. Min Act: -0.1700
Data Index: 816699 (C4 (Web Text))
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4828. Min Range: -6.4828
Max Act: 6.1391. Min Act: -0.1700
Data Index: 401054 (C4 (Web Text))
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4828. Min Range: -6.4828
Max Act: 6.1391. Min Act: -0.1700
Data Index: 1086319 (C4 (Web Text))
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4828. Min Range: -6.4828
Max Act: 6.0453. Min Act: -0.1700
Data Index: 1139882 (C4 (Web Text))
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4828. Min Range: -6.4828
Max Act: 6.2016. Min Act: -0.1700
Data Index: 269743 (C4 (Web Text))
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4828. Min Range: -6.4828
Max Act: 6.0766. Min Act: -0.1700
Data Index: 596184 (C4 (Web Text))
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4828. Min Range: -6.4828
Max Act: 6.1078. Min Act: -0.1700
Data Index: 700387 (C4 (Web Text))
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4828. Min Range: -6.4828
Max Act: 6.1078. Min Act: -0.1700
Data Index: 796421 (C4 (Web Text))
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4828. Min Range: -6.4828
Max Act: 6.0141. Min Act: -0.1700
Data Index: 877443 (C4 (Web Text))
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #19