Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 110 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.6686. Min Range: -2.6686
Max Act: 2.6686. Min Act: -0.1700
Data Index: 1452793 (Python Code)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6686. Min Range: -2.6686
Max Act: 2.6205. Min Act: -0.1700
Data Index: 1492487 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6686. Min Range: -2.6686
Max Act: 2.6044. Min Act: -0.1700
Data Index: 1444067 (Python Code)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6686. Min Range: -2.6686
Max Act: 2.6205. Min Act: -0.1700
Data Index: 1536829 (Python Code)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6686. Min Range: -2.6686
Max Act: 2.6044. Min Act: -0.1700
Data Index: 1449672 (Python Code)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6686. Min Range: -2.6686
Max Act: 2.6044. Min Act: -0.1700
Data Index: 1570657 (Python Code)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6686. Min Range: -2.6686
Max Act: 2.6044. Min Act: -0.1700
Data Index: 1455093 (Python Code)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6686. Min Range: -2.6686
Max Act: 2.6044. Min Act: -0.1700
Data Index: 1370240 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6686. Min Range: -2.6686
Max Act: 2.6044. Min Act: -0.1700
Data Index: 1409217 (Python Code)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6686. Min Range: -2.6686
Max Act: 2.6044. Min Act: -0.1700
Data Index: 1384808 (Python Code)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6686. Min Range: -2.6686
Max Act: 2.6044. Min Act: -0.1700
Data Index: 1528741 (Python Code)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6686. Min Range: -2.6686
Max Act: 2.6044. Min Act: -0.1700
Data Index: 1442690 (Python Code)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6686. Min Range: -2.6686
Max Act: 2.5883. Min Act: -0.1700
Data Index: 1638604 (Python Code)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6686. Min Range: -2.6686
Max Act: 2.6044. Min Act: -0.1700
Data Index: 1392972 (Python Code)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6686. Min Range: -2.6686
Max Act: 2.5883. Min Act: -0.1700
Data Index: 1459285 (Python Code)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6686. Min Range: -2.6686
Max Act: 2.5883. Min Act: -0.1700
Data Index: 1531813 (Python Code)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6686. Min Range: -2.6686
Max Act: 2.5722. Min Act: -0.1700
Data Index: 1520029 (Python Code)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6686. Min Range: -2.6686
Max Act: 2.5722. Min Act: -0.1700
Data Index: 1412726 (Python Code)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6686. Min Range: -2.6686
Max Act: 2.5883. Min Act: -0.1700
Data Index: 1540516 (Python Code)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6686. Min Range: -2.6686
Max Act: 2.5722. Min Act: -0.1700
Data Index: 1547802 (Python Code)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #19