Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2005 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 5.5896. Min Range: -5.5896
Max Act: 5.5896. Min Act: -0.1700
Data Index: 1300464 (C4 (Web Text))
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5896. Min Range: -5.5896
Max Act: 5.4958. Min Act: -0.1700
Data Index: 2266 (C4 (Web Text))
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5896. Min Range: -5.5896
Max Act: 5.4958. Min Act: -0.1700
Data Index: 1262872 (C4 (Web Text))
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5896. Min Range: -5.5896
Max Act: 5.4333. Min Act: -0.1700
Data Index: 1279461 (C4 (Web Text))
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5896. Min Range: -5.5896
Max Act: 5.4646. Min Act: -0.1700
Data Index: 274357 (C4 (Web Text))
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5896. Min Range: -5.5896
Max Act: 5.4021. Min Act: -0.1700
Data Index: 298737 (C4 (Web Text))
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5896. Min Range: -5.5896
Max Act: 5.4646. Min Act: -0.1700
Data Index: 223576 (C4 (Web Text))
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5896. Min Range: -5.5896
Max Act: 5.4333. Min Act: -0.1700
Data Index: 173756 (C4 (Web Text))
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5896. Min Range: -5.5896
Max Act: 5.4021. Min Act: -0.1700
Data Index: 1293103 (C4 (Web Text))
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5896. Min Range: -5.5896
Max Act: 5.4021. Min Act: -0.1700
Data Index: 1140101 (C4 (Web Text))
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5896. Min Range: -5.5896
Max Act: 5.4021. Min Act: -0.1700
Data Index: 527264 (C4 (Web Text))
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5896. Min Range: -5.5896
Max Act: 5.4021. Min Act: -0.1700
Data Index: 642667 (C4 (Web Text))
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5896. Min Range: -5.5896
Max Act: 5.3396. Min Act: -0.1700
Data Index: 985666 (C4 (Web Text))
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5896. Min Range: -5.5896
Max Act: 5.4021. Min Act: -0.1700
Data Index: 216989 (C4 (Web Text))
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5896. Min Range: -5.5896
Max Act: 5.3396. Min Act: -0.1700
Data Index: 1261695 (C4 (Web Text))
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5896. Min Range: -5.5896
Max Act: 5.3708. Min Act: -0.1700
Data Index: 504675 (C4 (Web Text))
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5896. Min Range: -5.5896
Max Act: 5.3708. Min Act: -0.1700
Data Index: 1129814 (C4 (Web Text))
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5896. Min Range: -5.5896
Max Act: 5.2771. Min Act: -0.1700
Data Index: 139855 (C4 (Web Text))
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5896. Min Range: -5.5896
Max Act: 5.3396. Min Act: -0.1700
Data Index: 154802 (C4 (Web Text))
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5896. Min Range: -5.5896
Max Act: 5.3396. Min Act: -0.1700
Data Index: 20486 (C4 (Web Text))
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #19