Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2014 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.9859. Min Range: -2.9859
Max Act: 2.9859. Min Act: -0.1700
Data Index: 1443036 (Python Code)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9859. Min Range: -2.9859
Max Act: 2.8909. Min Act: -0.1700
Data Index: 1542465 (Python Code)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9859. Min Range: -2.9859
Max Act: 2.8432. Min Act: -0.1700
Data Index: 1432777 (Python Code)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9859. Min Range: -2.9859
Max Act: 2.8432. Min Act: -0.1700
Data Index: 1547805 (Python Code)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9859. Min Range: -2.9859
Max Act: 2.8273. Min Act: -0.1700
Data Index: 1643947 (Python Code)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9859. Min Range: -2.9859
Max Act: 2.8273. Min Act: -0.1700
Data Index: 1445626 (Python Code)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9859. Min Range: -2.9859
Max Act: 2.7955. Min Act: -0.1700
Data Index: 1496639 (Python Code)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9859. Min Range: -2.9859
Max Act: 2.8114. Min Act: -0.1700
Data Index: 1362767 (Python Code)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9859. Min Range: -2.9859
Max Act: 2.7795. Min Act: -0.1700
Data Index: 1505558 (Python Code)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9859. Min Range: -2.9859
Max Act: 2.7955. Min Act: -0.1700
Data Index: 1442794 (Python Code)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9859. Min Range: -2.9859
Max Act: 2.7795. Min Act: -0.1700
Data Index: 1504949 (Python Code)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9859. Min Range: -2.9859
Max Act: 2.7955. Min Act: -0.1700
Data Index: 1581074 (Python Code)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9859. Min Range: -2.9859
Max Act: 2.7795. Min Act: -0.1700
Data Index: 1372083 (Python Code)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9859. Min Range: -2.9859
Max Act: 2.7955. Min Act: -0.1700
Data Index: 1576300 (Python Code)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9859. Min Range: -2.9859
Max Act: 2.7955. Min Act: -0.1700
Data Index: 1388495 (Python Code)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9859. Min Range: -2.9859
Max Act: 2.7795. Min Act: -0.1700
Data Index: 1566617 (Python Code)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9859. Min Range: -2.9859
Max Act: 2.7795. Min Act: -0.1700
Data Index: 1423323 (Python Code)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9859. Min Range: -2.9859
Max Act: 2.7476. Min Act: -0.1700
Data Index: 1482361 (Python Code)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9859. Min Range: -2.9859
Max Act: 2.7476. Min Act: -0.1700
Data Index: 1429849 (Python Code)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9859. Min Range: -2.9859
Max Act: 2.7317. Min Act: -0.1700
Data Index: 1605793 (Python Code)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #19