Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1446 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.9617. Min Range: -4.9617
Max Act: 4.9617. Min Act: -0.1700
Data Index: 822895 (C4 (Web Text))
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9617. Min Range: -4.9617
Max Act: 4.9617. Min Act: -0.1700
Data Index: 433742 (C4 (Web Text))
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9617. Min Range: -4.9617
Max Act: 4.8992. Min Act: -0.1700
Data Index: 371349 (C4 (Web Text))
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9617. Min Range: -4.9617
Max Act: 4.9305. Min Act: -0.1700
Data Index: 600177 (C4 (Web Text))
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9617. Min Range: -4.9617
Max Act: 4.9617. Min Act: -0.1700
Data Index: 131065 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9617. Min Range: -4.9617
Max Act: 4.8680. Min Act: -0.1700
Data Index: 337644 (C4 (Web Text))
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9617. Min Range: -4.9617
Max Act: 4.8680. Min Act: -0.1700
Data Index: 238779 (C4 (Web Text))
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9617. Min Range: -4.9617
Max Act: 4.8367. Min Act: -0.1700
Data Index: 805368 (C4 (Web Text))
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9617. Min Range: -4.9617
Max Act: 4.8367. Min Act: -0.1700
Data Index: 264302 (C4 (Web Text))
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9617. Min Range: -4.9617
Max Act: 4.7742. Min Act: -0.1700
Data Index: 418329 (C4 (Web Text))
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9617. Min Range: -4.9617
Max Act: 4.7430. Min Act: -0.1700
Data Index: 995984 (C4 (Web Text))
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9617. Min Range: -4.9617
Max Act: 4.7430. Min Act: -0.1700
Data Index: 1165000 (C4 (Web Text))
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9617. Min Range: -4.9617
Max Act: 4.8680. Min Act: -0.1700
Data Index: 29042 (C4 (Web Text))
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9617. Min Range: -4.9617
Max Act: 4.6180. Min Act: -0.1700
Data Index: 980507 (C4 (Web Text))
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9617. Min Range: -4.9617
Max Act: 4.7117. Min Act: -0.1700
Data Index: 783448 (C4 (Web Text))
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9617. Min Range: -4.9617
Max Act: 4.7117. Min Act: -0.1700
Data Index: 678649 (C4 (Web Text))
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9617. Min Range: -4.9617
Max Act: 4.6805. Min Act: -0.1700
Data Index: 499690 (C4 (Web Text))
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9617. Min Range: -4.9617
Max Act: 4.7430. Min Act: -0.1700
Data Index: 912410 (C4 (Web Text))
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9617. Min Range: -4.9617
Max Act: 4.7117. Min Act: -0.1700
Data Index: 1246887 (C4 (Web Text))
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9617. Min Range: -4.9617
Max Act: 4.6492. Min Act: -0.1700
Data Index: 266310 (C4 (Web Text))
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #19