Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 71 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.5698. Min Range: -4.5698
Max Act: 4.5698. Min Act: -0.1700
Data Index: 1434715 (Python Code)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5698. Min Range: -4.5698
Max Act: 4.5073. Min Act: -0.1700
Data Index: 556200 (C4 (Web Text))
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5698. Min Range: -4.5698
Max Act: 4.3198. Min Act: -0.1700
Data Index: 1368412 (Python Code)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5698. Min Range: -4.5698
Max Act: 4.3198. Min Act: -0.1700
Data Index: 1560403 (Python Code)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5698. Min Range: -4.5698
Max Act: 4.1947. Min Act: -0.1700
Data Index: 426015 (C4 (Web Text))
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5698. Min Range: -4.5698
Max Act: 4.2572. Min Act: -0.1700
Data Index: 1376555 (Python Code)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5698. Min Range: -4.5698
Max Act: 4.0072. Min Act: -0.1700
Data Index: 1520298 (Python Code)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5698. Min Range: -4.5698
Max Act: 4.0072. Min Act: -0.1700
Data Index: 1500790 (Python Code)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5698. Min Range: -4.5698
Max Act: 4.0072. Min Act: -0.1700
Data Index: 1612868 (Python Code)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5698. Min Range: -4.5698
Max Act: 3.8977. Min Act: -0.1700
Data Index: 1477918 (Python Code)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5698. Min Range: -4.5698
Max Act: 3.9759. Min Act: -0.1700
Data Index: 202552 (C4 (Web Text))
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5698. Min Range: -4.5698
Max Act: 3.8977. Min Act: -0.1700
Data Index: 1611658 (Python Code)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5698. Min Range: -4.5698
Max Act: 3.8508. Min Act: -0.1700
Data Index: 1551177 (Python Code)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5698. Min Range: -4.5698
Max Act: 3.9290. Min Act: -0.1700
Data Index: 1067579 (C4 (Web Text))
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5698. Min Range: -4.5698
Max Act: 3.9134. Min Act: -0.1700
Data Index: 991351 (C4 (Web Text))
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5698. Min Range: -4.5698
Max Act: 3.8977. Min Act: -0.1700
Data Index: 198932 (C4 (Web Text))
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5698. Min Range: -4.5698
Max Act: 3.8821. Min Act: -0.1700
Data Index: 143614 (C4 (Web Text))
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5698. Min Range: -4.5698
Max Act: 3.7883. Min Act: -0.1700
Data Index: 1166655 (C4 (Web Text))
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5698. Min Range: -4.5698
Max Act: 3.7883. Min Act: -0.1700
Data Index: 1592519 (Python Code)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5698. Min Range: -4.5698
Max Act: 3.8508. Min Act: -0.1700
Data Index: 381334 (C4 (Web Text))
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #19