Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 192 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.1578. Min Range: -4.1578
Max Act: 4.1578. Min Act: -0.1700
Data Index: 1336382 (C4 (Web Text))
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1578. Min Range: -4.1578
Max Act: 4.0327. Min Act: -0.1700
Data Index: 126683 (C4 (Web Text))
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1578. Min Range: -4.1578
Max Act: 4.0015. Min Act: -0.1700
Data Index: 1459615 (Python Code)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1578. Min Range: -4.1578
Max Act: 4.0640. Min Act: -0.1700
Data Index: 1297263 (C4 (Web Text))
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1578. Min Range: -4.1578
Max Act: 4.0640. Min Act: -0.1700
Data Index: 1162813 (C4 (Web Text))
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1578. Min Range: -4.1578
Max Act: 4.0640. Min Act: -0.1700
Data Index: 1293025 (C4 (Web Text))
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1578. Min Range: -4.1578
Max Act: 4.0327. Min Act: -0.1700
Data Index: 1603842 (Python Code)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1578. Min Range: -4.1578
Max Act: 4.0327. Min Act: -0.1700
Data Index: 677425 (C4 (Web Text))
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1578. Min Range: -4.1578
Max Act: 4.0015. Min Act: -0.1700
Data Index: 1225319 (C4 (Web Text))
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1578. Min Range: -4.1578
Max Act: 4.0015. Min Act: -0.1700
Data Index: 1646271 (Python Code)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1578. Min Range: -4.1578
Max Act: 4.0015. Min Act: -0.1700
Data Index: 1590434 (Python Code)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1578. Min Range: -4.1578
Max Act: 4.0327. Min Act: -0.1700
Data Index: 859139 (C4 (Web Text))
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1578. Min Range: -4.1578
Max Act: 4.0015. Min Act: -0.1700
Data Index: 1133686 (C4 (Web Text))
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1578. Min Range: -4.1578
Max Act: 3.9702. Min Act: -0.1700
Data Index: 1392430 (Python Code)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1578. Min Range: -4.1578
Max Act: 3.9389. Min Act: -0.1700
Data Index: 1423377 (Python Code)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1578. Min Range: -4.1578
Max Act: 3.9077. Min Act: -0.1700
Data Index: 1417394 (Python Code)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1578. Min Range: -4.1578
Max Act: 3.9389. Min Act: -0.1700
Data Index: 1579076 (Python Code)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1578. Min Range: -4.1578
Max Act: 3.9077. Min Act: -0.1700
Data Index: 1600771 (Python Code)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1578. Min Range: -4.1578
Max Act: 3.9389. Min Act: -0.1700
Data Index: 1201327 (C4 (Web Text))
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1578. Min Range: -4.1578
Max Act: 3.9077. Min Act: -0.1700
Data Index: 1542697 (Python Code)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #19