Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1880 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.4844. Min Range: -2.4844
Max Act: 2.4844. Min Act: -0.1700
Data Index: 1553857 (Python Code)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4844. Min Range: -2.4844
Max Act: 2.4681. Min Act: -0.1700
Data Index: 1492416 (Python Code)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4844. Min Range: -2.4844
Max Act: 2.4519. Min Act: -0.1700
Data Index: 1526778 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4844. Min Range: -2.4844
Max Act: 2.4031. Min Act: -0.1700
Data Index: 1443773 (Python Code)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4844. Min Range: -2.4844
Max Act: 2.3867. Min Act: -0.1700
Data Index: 764569 (C4 (Web Text))
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4844. Min Range: -2.4844
Max Act: 2.3867. Min Act: -0.1700
Data Index: 1503771 (Python Code)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4844. Min Range: -2.4844
Max Act: 2.3867. Min Act: -0.1700
Data Index: 163451 (C4 (Web Text))
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4844. Min Range: -2.4844
Max Act: 2.3704. Min Act: -0.1700
Data Index: 1620528 (Python Code)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4844. Min Range: -2.4844
Max Act: 2.3704. Min Act: -0.1700
Data Index: 1504829 (Python Code)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4844. Min Range: -2.4844
Max Act: 2.3704. Min Act: -0.1700
Data Index: 1493985 (Python Code)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4844. Min Range: -2.4844
Max Act: 2.3704. Min Act: -0.1700
Data Index: 1511299 (Python Code)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4844. Min Range: -2.4844
Max Act: 2.3541. Min Act: -0.1700
Data Index: 1441901 (Python Code)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4844. Min Range: -2.4844
Max Act: 2.3704. Min Act: -0.1700
Data Index: 1520891 (Python Code)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4844. Min Range: -2.4844
Max Act: 2.3704. Min Act: -0.1700
Data Index: 1364912 (Python Code)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4844. Min Range: -2.4844
Max Act: 2.3541. Min Act: -0.1700
Data Index: 1596616 (Python Code)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4844. Min Range: -2.4844
Max Act: 2.3541. Min Act: -0.1700
Data Index: 1596919 (Python Code)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4844. Min Range: -2.4844
Max Act: 2.3704. Min Act: -0.1700
Data Index: 1618004 (Python Code)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4844. Min Range: -2.4844
Max Act: 2.3541. Min Act: -0.1700
Data Index: 1631344 (Python Code)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4844. Min Range: -2.4844
Max Act: 2.3541. Min Act: -0.1700
Data Index: 1420819 (Python Code)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4844. Min Range: -2.4844
Max Act: 2.3541. Min Act: -0.1700
Data Index: 1480285 (Python Code)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #19